2024-02-28T07:53:53,948 Created temporary directory: /tmp/pip-build-tracker-tlab4r61
2024-02-28T07:53:53,949 Initialized build tracking at /tmp/pip-build-tracker-tlab4r61
2024-02-28T07:53:53,949 Created build tracker: /tmp/pip-build-tracker-tlab4r61
2024-02-28T07:53:53,950 Entered build tracker: /tmp/pip-build-tracker-tlab4r61
2024-02-28T07:53:53,950 Created temporary directory: /tmp/pip-wheel-1e0qhhza
2024-02-28T07:53:53,954 Created temporary directory: /tmp/pip-ephem-wheel-cache-rhbxdfpo
2024-02-28T07:53:53,975 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple
2024-02-28T07:53:53,979 2 location(s) to search for versions of llama-cpp-python:
2024-02-28T07:53:53,979 * https://pypi.org/simple/llama-cpp-python/
2024-02-28T07:53:53,979 * https://www.piwheels.org/simple/llama-cpp-python/
2024-02-28T07:53:53,980 Fetching project page and analyzing links: https://pypi.org/simple/llama-cpp-python/
2024-02-28T07:53:53,981 Getting page https://pypi.org/simple/llama-cpp-python/
2024-02-28T07:53:53,982 Found index url https://pypi.org/simple/
2024-02-28T07:53:54,133 Fetched page https://pypi.org/simple/llama-cpp-python/ as application/vnd.pypi.simple.v1+json
2024-02-28T07:53:54,156   Found link https://files.pythonhosted.org/packages/17/9c/813d8c83d81cb9ab42e5ee66657f8d3670bacdcd67df4aa7728e8dccbcfd/llama_cpp_python-0.1.1.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.1
2024-02-28T07:53:54,157   Found link https://files.pythonhosted.org/packages/42/22/07711b8fc85ed188182c923aa424254a451ee23a58d6c45a033e05e57f9a/llama_cpp_python-0.1.2.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.2
2024-02-28T07:53:54,157   Found link https://files.pythonhosted.org/packages/13/a2/a3a6e665905992e2ed2c79b7af2dce4a36f23c5147959f0f56d9bd72543c/llama_cpp_python-0.1.3.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.3
2024-02-28T07:53:54,158   Found link https://files.pythonhosted.org/packages/00/b6/3069b31e8cd0073685aa059e161e4b8dc3a4e3c77c4f8f433fa5ebc01655/llama_cpp_python-0.1.4.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.4
2024-02-28T07:53:54,159   Found link https://files.pythonhosted.org/packages/cd/32/e2380800128e64542f719c3d7287b2818e7234e268298b95273164cb0a3d/llama_cpp_python-0.1.5.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.5
2024-02-28T07:53:54,160   Found link https://files.pythonhosted.org/packages/9f/d3/9904d8616a5af9515b8852c441472c930b780db1879f13cae240bd4eb05f/llama_cpp_python-0.1.6.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.6
2024-02-28T07:53:54,160   Found link https://files.pythonhosted.org/packages/20/ff/c192e4469e14be86d3b11fdee4b56aca486033e4256174e2cf8425840e54/llama_cpp_python-0.1.7.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.7
2024-02-28T07:53:54,161   Found link https://files.pythonhosted.org/packages/7e/3b/b5f7e1ec5f43a4e980733c63bd4f05e1b7e14fd3b7aa72d9ca91f2415323/llama_cpp_python-0.1.8.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.8
2024-02-28T07:53:54,162   Found link https://files.pythonhosted.org/packages/9f/24/45a5a3beee1354f668d916eb1a2146835a0eda4dbad0da45252170e105a6/llama_cpp_python-0.1.9.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.9
2024-02-28T07:53:54,163   Found link https://files.pythonhosted.org/packages/71/ad/e3f373300efdfbcd67dc3909512a5b80dd6c5f2092102cbea66bad75ec4d/llama_cpp_python-0.1.10.tar.gz (from https://pypi.org/simple/llama-cpp-python/), version: 0.1.10
2024-02-28T07:53:54,164   Found link https://files.pythonhosted.org/packages/bb/5e/c15d23176dd5783b1f62fd1b89c38fa655c9c1b524451e34a240fabffca8/llama_cpp_python-0.1.11.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.11
2024-02-28T07:53:54,165   Found link https://files.pythonhosted.org/packages/ad/61/91b0c968596bcca9b09c6e40a38852500d31ed5f8649e25cfab293dc9af0/llama_cpp_python-0.1.12.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.12
2024-02-28T07:53:54,166   Found link https://files.pythonhosted.org/packages/63/8f/1bb0a901a1be8c243e741a17ece1588615a1c5c4b9578ce80f12ce809d14/llama_cpp_python-0.1.13.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.13
2024-02-28T07:53:54,167   Found link https://files.pythonhosted.org/packages/25/bc/83364cb8c3fff7da82fadd10e0d1ec221278a5403ab4222dd0745bfa6709/llama_cpp_python-0.1.14.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.14
2024-02-28T07:53:54,168   Found link https://files.pythonhosted.org/packages/d8/6b/0b89436a26c2a7a5e1b57809d6f692c4f0afd87b19c31fe5425ddb19f54b/llama_cpp_python-0.1.15.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.15
2024-02-28T07:53:54,169   Found link https://files.pythonhosted.org/packages/7f/ef/aa0d2e4ef92173bf7e3539b5fa3338e7f9f88a66e7a90cb2f00052b7a9cb/llama_cpp_python-0.1.16.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.16
2024-02-28T07:53:54,169   Found link https://files.pythonhosted.org/packages/71/d6/bb0a4bb92abf16dee92a933b45ba16f0e6c0a1b63ee8877c678a54c373a8/llama_cpp_python-0.1.17.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.17
2024-02-28T07:53:54,170   Found link https://files.pythonhosted.org/packages/c2/08/7c12856cbe4523e518e280914674f4b65f5f62076408a7984b69d9771494/llama_cpp_python-0.1.18.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.18
2024-02-28T07:53:54,171   Found link https://files.pythonhosted.org/packages/63/48/977cd0ffdbfb9446e758c8c69aa49025a7477058d42bd30bef67f42c556c/llama_cpp_python-0.1.19.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.19
2024-02-28T07:53:54,172   Found link https://files.pythonhosted.org/packages/dc/2e/730cc405e0227ce6f49dd2bab4d6ce69963cb65bc3452fd33a552c9b8630/llama_cpp_python-0.1.20.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.20
2024-02-28T07:53:54,173   Found link https://files.pythonhosted.org/packages/52/1a/d122abc9571e09e17ad8909d2f8710ea0abe26ced1287ae82828fc80aaa3/llama_cpp_python-0.1.21.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.21
2024-02-28T07:53:54,174   Found link https://files.pythonhosted.org/packages/cf/94/4c35d7e3011ce86f063e3c754afd71f3a6f1f2a0ec9616deb55e8f3743a1/llama_cpp_python-0.1.22.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.22
2024-02-28T07:53:54,175   Found link https://files.pythonhosted.org/packages/03/6e/3e0768c396be6807b9e835c223ce37385d574eaf9e4d0ac80116325f6775/llama_cpp_python-0.1.23.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.23
2024-02-28T07:53:54,176   Found link https://files.pythonhosted.org/packages/bc/8b/618c42fdfa078a3cec9ed871b9c1bb6cca65b66e4e3ce0bf690f8109eaa1/llama_cpp_python-0.1.24.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.24
2024-02-28T07:53:54,177   Found link https://files.pythonhosted.org/packages/6c/64/bd9d98588aa8b6c49c0cfa1d0b4ef4ec5a1a05e4d8d67c1aed3587ae2e1a/llama_cpp_python-0.1.25.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.25
2024-02-28T07:53:54,178   Found link https://files.pythonhosted.org/packages/c1/cf/c81b3ba5340398820cc12c247e33f3f1ee15c4043794596968dc31ebac9c/llama_cpp_python-0.1.26.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.26
2024-02-28T07:53:54,178   Found link https://files.pythonhosted.org/packages/fa/b8/0a6fafae31b2c40997c282cd9220743c419dd8b372f09c57e551792bb899/llama_cpp_python-0.1.27.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.27
2024-02-28T07:53:54,179   Found link https://files.pythonhosted.org/packages/fb/6a/0c7421119d6e536ee1ca02ad5555dbbda7a38189333b0ac67f582cd5a84f/llama_cpp_python-0.1.28.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.28
2024-02-28T07:53:54,180   Found link https://files.pythonhosted.org/packages/fa/e3/3a12c770007f9a3c5903f7e2904aff4af5fa7d36cb06843c65cfaadccdd2/llama_cpp_python-0.1.29.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.29
2024-02-28T07:53:54,182   Found link https://files.pythonhosted.org/packages/e5/8e/b8dfcb10fdb1b2556a688cb23fd3d1b7b60c2b24ddc1cb9fc61a915c94d0/llama_cpp_python-0.1.30.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.30
2024-02-28T07:53:54,182   Found link https://files.pythonhosted.org/packages/c9/46/e37f0120bf5996b644c373c8fea9d2bf31ceb30e18724f2ae0876cb25b96/llama_cpp_python-0.1.31.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.31
2024-02-28T07:53:54,183   Found link https://files.pythonhosted.org/packages/39/f2/9d9c98ccb9ffe2ca7c9aeef235d5e45a4694f3148dfc9559e672c346f6ea/llama_cpp_python-0.1.32.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.32
2024-02-28T07:53:54,184   Found link https://files.pythonhosted.org/packages/70/b3/a1497e783b921cc8cd0d2f7fabe9d0b5c2bf95ab9fd56503d282862ce720/llama_cpp_python-0.1.33.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.33
2024-02-28T07:53:54,185   Found link https://files.pythonhosted.org/packages/b3/f0/82690e424b3fdb0d1738f312095a7a88cbe06cb910be9c5f5d4c7e3bdde8/llama_cpp_python-0.1.34.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.34
2024-02-28T07:53:54,186   Found link https://files.pythonhosted.org/packages/e9/47/013240af1272400ad49422f8ebfc47476a4d82e3375dd05dbd1440da3c50/llama_cpp_python-0.1.35.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.35
2024-02-28T07:53:54,187   Found link https://files.pythonhosted.org/packages/1b/ea/3f2aff10fd7195c6bc8c52375d9ff027a551151569c50e0d47581b14b7c1/llama_cpp_python-0.1.36.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.36
2024-02-28T07:53:54,188   Found link https://files.pythonhosted.org/packages/5d/10/e037dc290ed7435dd6f5fa5dcce2453f1cf145b84f1e8e40d0a63ac62aa2/llama_cpp_python-0.1.37.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.37
2024-02-28T07:53:54,189   Found link https://files.pythonhosted.org/packages/e6/2a/d898551013b9f0863b8134dbcb5863a306f5d9c2ad4a394c68a2988a77a0/llama_cpp_python-0.1.38.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.38
2024-02-28T07:53:54,190   Found link https://files.pythonhosted.org/packages/5a/41/955ac2e592949ca95a29efc5f544afcbc9ca3fc5484cb0272837d98c6b5a/llama_cpp_python-0.1.39.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.39
2024-02-28T07:53:54,190   Found link https://files.pythonhosted.org/packages/fc/2c/62c5ce16f88348f928320565cf6c0dfe8220a03615bff14e47e4f3b4e439/llama_cpp_python-0.1.40.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.40
2024-02-28T07:53:54,191   Found link https://files.pythonhosted.org/packages/d1/fe/852d447828bdcdfe1c8aa88061517b5de9e5c12389dd852076d5c913936a/llama_cpp_python-0.1.41.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.41
2024-02-28T07:53:54,192   Found link https://files.pythonhosted.org/packages/8d/bb/48129f3696fcc125fac1c91a5a6df5ab472e561d74ed5818e6fca748a432/llama_cpp_python-0.1.42.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.42
2024-02-28T07:53:54,193   Found link https://files.pythonhosted.org/packages/eb/43/ac841dc1a3f5f618e4546ce69fe7da0d976cb141c92b8d1f735f2baf0b85/llama_cpp_python-0.1.43.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.43
2024-02-28T07:53:54,194   Found link https://files.pythonhosted.org/packages/29/69/b73ae145d6f40683656f537b8526ca27e8348c7ff9af9c014a6a723fda5f/llama_cpp_python-0.1.44.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.44
2024-02-28T07:53:54,195   Found link https://files.pythonhosted.org/packages/62/b7/299b9d537037a95d4433498c73c1a8024de230a26d0c94b3e889364038d4/llama_cpp_python-0.1.45.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.45
2024-02-28T07:53:54,196   Found link https://files.pythonhosted.org/packages/c2/12/450986c9506525096cc77fcb6584ee02ec7d0017df0d34e6c79b9dba5a58/llama_cpp_python-0.1.46.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.46
2024-02-28T07:53:54,197   Found link https://files.pythonhosted.org/packages/28/95/11fcced0778cb9b82a81cd61c93760a379527ef13d90a66254fdc2e982df/llama_cpp_python-0.1.47.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.47
2024-02-28T07:53:54,198   Found link https://files.pythonhosted.org/packages/35/04/63f43ff24bd8948abbe2d7c9c3e3d235c0e7501ec8b1e72d01676051f75d/llama_cpp_python-0.1.48.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.48
2024-02-28T07:53:54,199   Found link https://files.pythonhosted.org/packages/1b/60/be610e7e95eb53e949ac74024b30d5fa763244928b07a16815d16643b7ab/llama_cpp_python-0.1.49.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.49
2024-02-28T07:53:54,200   Found link https://files.pythonhosted.org/packages/82/2c/9614ef76422168fde5326095559f271a22b1926185add8ae739901e113b9/llama_cpp_python-0.1.50.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.50
2024-02-28T07:53:54,201   Found link https://files.pythonhosted.org/packages/f9/65/78748102cca92fb148e111c41827433ecc2cb79eed9de0a72a4d7a4361c0/llama_cpp_python-0.1.51.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.51
2024-02-28T07:53:54,202   Found link https://files.pythonhosted.org/packages/87/cb/21c00f6f5b3a680671cb9c7e7ec5e07a6c03df70e28cd54f6197744c1f12/llama_cpp_python-0.1.52.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.52
2024-02-28T07:53:54,202   Found link https://files.pythonhosted.org/packages/d6/8d/d1700e37bd9b8965154e12008620e3bd3ed7ed585ad86650294074577629/llama_cpp_python-0.1.53.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.53
2024-02-28T07:53:54,203   Found link https://files.pythonhosted.org/packages/24/a7/e2904574d326e24338aab2e5fd618f007ef8b51c2a29618791f9c24269e2/llama_cpp_python-0.1.54.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.54
2024-02-28T07:53:54,204   Found link https://files.pythonhosted.org/packages/b2/9b/15a40971444775d7aa5aee934991fa97eee285ae3a77c98c70c382f2ed60/llama_cpp_python-0.1.55.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.55
2024-02-28T07:53:54,206   Found link https://files.pythonhosted.org/packages/2e/d7/36eccf10a611e2f3040cec775b9734ea51cf9938b2d911e30cbf71dd321b/llama_cpp_python-0.1.56.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.56
2024-02-28T07:53:54,207   Found link https://files.pythonhosted.org/packages/4d/e5/b337c9e7330695eb5efa2329d25b2d964fe10364429698c89140729ebaaf/llama_cpp_python-0.1.57.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.57
2024-02-28T07:53:54,207   Found link https://files.pythonhosted.org/packages/91/0f/8156d3f1b6bbbea68f28df5e325a2863ed736362b0f93f7936acba424e70/llama_cpp_python-0.1.59.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.59
2024-02-28T07:53:54,209   Found link https://files.pythonhosted.org/packages/e9/18/9531e94f7a4cd402cf200a9e6257fc08d162b8a8d57adf6f4049f60ba05b/llama_cpp_python-0.1.61.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.61
2024-02-28T07:53:54,210   Found link https://files.pythonhosted.org/packages/cc/ed/fe9bbe6c4f2156fc5e887d9e669872bc1722f80a2932a78a8166d7a82877/llama_cpp_python-0.1.62.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.62
2024-02-28T07:53:54,211   Found link https://files.pythonhosted.org/packages/a8/01/7e39377ad0d20d2379b01b7019aad9b3595ea21ced1705ccc49c78936088/llama_cpp_python-0.1.63.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.63
2024-02-28T07:53:54,212   Found link https://files.pythonhosted.org/packages/ad/c1/4083e90a0b31e1abb72d3f00f8d1403bdc9384301e1e370d0915f73519f5/llama_cpp_python-0.1.64.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.64
2024-02-28T07:53:54,213   Found link https://files.pythonhosted.org/packages/84/7d/a659b65132db354147654bf2b6b2c8820b25aa10833b4849ec6b66e69117/llama_cpp_python-0.1.65.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.65
2024-02-28T07:53:54,214   Found link https://files.pythonhosted.org/packages/59/43/6dfbaed1f70ef013279b03e436b8f58f9f2ab0835e04034927fc31bb8fc9/llama_cpp_python-0.1.66.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.66
2024-02-28T07:53:54,215   Found link https://files.pythonhosted.org/packages/96/79/3dbc78c1a6e14d088673d21549a736aa27ca69ef1734541a07c36f349cf7/llama_cpp_python-0.1.67.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.67
2024-02-28T07:53:54,216   Found link https://files.pythonhosted.org/packages/87/0a/f99cdd3befe25e414f9a758fb89bf70ca5278d68430af140391fc262bb55/llama_cpp_python-0.1.68.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.68
2024-02-28T07:53:54,217   Found link https://files.pythonhosted.org/packages/e6/a2/86200ff91d374311fbb704079d95927edacfc47592ae34c3c48a47863eea/llama_cpp_python-0.1.69.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.69
2024-02-28T07:53:54,218   Found link https://files.pythonhosted.org/packages/78/60/5cfb3842ef25db4ee1555dc2a70b99c569ad27c0438e7d9704c1672828b8/llama_cpp_python-0.1.70.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.70
2024-02-28T07:53:54,219   Found link https://files.pythonhosted.org/packages/4b/d1/24602670353e3f08f07c9bf36dca5ef5466ac3c0d27b5d5be0685e8032a7/llama_cpp_python-0.1.71.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.71
2024-02-28T07:53:54,220   Found link https://files.pythonhosted.org/packages/7f/59/b17486fa68bd3bce14fad89e049ea2700cf9ca36e7710d9380e2facbe182/llama_cpp_python-0.1.72.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.72
2024-02-28T07:53:54,221   Found link https://files.pythonhosted.org/packages/c5/c5/3bcee8d4fa2a3faef625dd1223e945ab15aa7d2f180158f30762eaa597b1/llama_cpp_python-0.1.73.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.73
2024-02-28T07:53:54,222   Found link https://files.pythonhosted.org/packages/73/09/99e6bf5d56e96a15a67628b15b705afbddf27279e6738018c4d7866d05c7/llama_cpp_python-0.1.74.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.74
2024-02-28T07:53:54,223   Found link https://files.pythonhosted.org/packages/b3/61/85c4defcdd3157004611feff6c95e8b4776d8671ca754ff2ed91fbc85154/llama_cpp_python-0.1.76.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.76
2024-02-28T07:53:54,224   Found link https://files.pythonhosted.org/packages/28/57/6db0db4582e31ced78487c6f28a4ee127fe38a22a85c573c39c7e5a03e2f/llama_cpp_python-0.1.77.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.77
2024-02-28T07:53:54,225   Found link https://files.pythonhosted.org/packages/dd/98/3d2382ac0b462b175519de360c57d514fbe5d33a5e67e42e82dc03bfb0f9/llama_cpp_python-0.1.78.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.78
2024-02-28T07:53:54,226   Found link https://files.pythonhosted.org/packages/f2/85/39c90a6b2306fbf91fc9dd2346bb4599c57e5c29aec15981fe5d662cef34/llama_cpp_python-0.1.79.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.79
2024-02-28T07:53:54,227   Found link https://files.pythonhosted.org/packages/af/c7/e3cee337dc44024bece8faf7683e40d015bae55b0dfaddd1a97ab4d1b432/llama_cpp_python-0.1.80.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.80
2024-02-28T07:53:54,227   Found link https://files.pythonhosted.org/packages/ae/92/c10ee59095bc1336edbecc8f6eea98d9d2f4df1d944b9df9b4484ea268ae/llama_cpp_python-0.1.81.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.81
2024-02-28T07:53:54,228   Found link https://files.pythonhosted.org/packages/81/b5/b63dbe0b799b9063208543a84b0e99b622f8a8d19de9564fc1d2877e1c9e/llama_cpp_python-0.1.82.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.82
2024-02-28T07:53:54,229   Found link https://files.pythonhosted.org/packages/6e/c7/651fa47b77d2189a46b00caa44627d17476bf41bcbeb0b72906295d6de79/llama_cpp_python-0.1.83.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.83
2024-02-28T07:53:54,230   Found link https://files.pythonhosted.org/packages/39/f2/a64d37bdaecb2ad66cfc2faab95201acf66b537affbd042656b27dc135f4/llama_cpp_python-0.1.84.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.84
2024-02-28T07:53:54,231   Found link https://files.pythonhosted.org/packages/ed/f2/2fb3b4c3886de5d1bcfbd258932159e374d1d9a0d52d6850805e26cc9fc2/llama_cpp_python-0.1.85.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.7), version: 0.1.85
2024-02-28T07:53:54,232   Found link https://files.pythonhosted.org/packages/5b/a6/a49b40d4c0ac9aa703bf11e5783d38beb3924a6ba5165a393518646894c9/llama_cpp_python-0.2.0.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.0
2024-02-28T07:53:54,233   Found link https://files.pythonhosted.org/packages/e4/3a/7c65dbed3913086ec0a84549acdd4002ef4e1ef9fbb1d31596a4c1fd64a3/llama_cpp_python-0.2.1.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.1
2024-02-28T07:53:54,234   Found link https://files.pythonhosted.org/packages/d0/28/ef9e91c4ed9e96a2a0bcd6a8327f2d039745b59946eccc6ccb1a9ee2dedf/llama_cpp_python-0.2.2.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.2
2024-02-28T07:53:54,235   Found link https://files.pythonhosted.org/packages/99/e6/19d9c978dc634d91b05416c8fc502171af6b27a20683669048afa5738b74/llama_cpp_python-0.2.3.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.3
2024-02-28T07:53:54,236   Found link https://files.pythonhosted.org/packages/7b/26/be5c224560ccbe64592afbdbe0710ae5b0a8413e1416cc8c2c0b093b713b/llama_cpp_python-0.2.4.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.4
2024-02-28T07:53:54,237   Found link https://files.pythonhosted.org/packages/04/9d/1f8fe06199b5fda5a691f23ef5622b32d5fe717da748f4fc2c9cbde60223/llama_cpp_python-0.2.5.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.5
2024-02-28T07:53:54,238   Found link https://files.pythonhosted.org/packages/ff/ca/8c45e45abb21069f6274efe3f1cf0aca29a1fd089fec6acf924ee4a67c46/llama_cpp_python-0.2.6.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.6
2024-02-28T07:53:54,239   Found link https://files.pythonhosted.org/packages/b1/78/bd5e6653102ea16ce53a044cec606f257811da99c9c2a760af6a93cdfef3/llama_cpp_python-0.2.7.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.7
2024-02-28T07:53:54,240   Found link https://files.pythonhosted.org/packages/6d/60/edbd982673a71c6c27fa6818914ad61c6171d165de4e777d489539f1d959/llama_cpp_python-0.2.8.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.8
2024-02-28T07:53:54,241   Found link https://files.pythonhosted.org/packages/98/2e/357d936ff7418591c56a27b9472e2b3581bd9eeb90c4221580fae5e00588/llama_cpp_python-0.2.9.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.9
2024-02-28T07:53:54,242   Found link https://files.pythonhosted.org/packages/d4/a2/ff96c80f91d7d534a6b65517247c09680b1bbf064d6388feda9aac3201dd/llama_cpp_python-0.2.10.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.10
2024-02-28T07:53:54,243   Found link https://files.pythonhosted.org/packages/5b/b9/1ea446f1dcccb13313ea1e651c73bd5cc4db2aabf6cae1894064bddf1fc4/llama_cpp_python-0.2.11.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.11
2024-02-28T07:53:54,244   Found link https://files.pythonhosted.org/packages/11/35/0185e28cfcdb59ab17e09a6cc6e19c7271db236ee1c9d41143a082b463b7/llama_cpp_python-0.2.12.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.12
2024-02-28T07:53:54,245   Found link https://files.pythonhosted.org/packages/da/58/55a26595009d76237273b340d718e04d9a33c5afd440e45552f45a16b1d9/llama_cpp_python-0.2.13.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.13
2024-02-28T07:53:54,245   Found link https://files.pythonhosted.org/packages/82/2c/e742d611024256b5540380e7a62cd1fdc3cc1b47f5d2b86610f545804acd/llama_cpp_python-0.2.14.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.14
2024-02-28T07:53:54,246   Found link https://files.pythonhosted.org/packages/0c/e9/0d48a445430bed484791f76a4ab1d7950e57468127a3ee6a6ec494f46ae5/llama_cpp_python-0.2.15.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.15
2024-02-28T07:53:54,247   Found link https://files.pythonhosted.org/packages/a8/3e/b0bd26d0d0d0dd9187a6e4e46c2744c1d7d52cc2834b35db61776af00219/llama_cpp_python-0.2.16.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.16
2024-02-28T07:53:54,248   Found link https://files.pythonhosted.org/packages/d1/2c/e75e2e5b08b805d23066f1c1f8dbb1777a5bd3b43f057d16d4b2634d9ae1/llama_cpp_python-0.2.17.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.17
2024-02-28T07:53:54,249   Found link https://files.pythonhosted.org/packages/1b/be/3ce85cdf2f3b7c035ca52e0158b98d244d4ce40a51908b22e0b45c3ef75f/llama_cpp_python-0.2.18.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.18
2024-02-28T07:53:54,250   Found link https://files.pythonhosted.org/packages/9d/1a/f74ce61893791530a9af61fe8925bd569d8fb087545dc1973d617c03ce11/llama_cpp_python-0.2.19.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.19
2024-02-28T07:53:54,251   Found link https://files.pythonhosted.org/packages/f0/6a/3e161b68097fe2f9901e01dc7ec2afb4753699495004a37d2abdc3b1fd07/llama_cpp_python-0.2.20.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.20
2024-02-28T07:53:54,252   Found link https://files.pythonhosted.org/packages/15/7a/49906adb90113f628c1f07dc746ca0978b8aa99a8f7325a8d961ce2a1919/llama_cpp_python-0.2.22.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.22
2024-02-28T07:53:54,253   Found link https://files.pythonhosted.org/packages/9b/30/fb7cd2d9a395d64f39b25eb36ba86163fd5bbb3c1427b9f2381b7d798d3a/llama_cpp_python-0.2.23.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.23
2024-02-28T07:53:54,254   Found link https://files.pythonhosted.org/packages/fe/fd/498415767be24e802135c409922c0072947adc5d73ea85ce6c98c42f2e63/llama_cpp_python-0.2.24.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.24
2024-02-28T07:53:54,255   Found link https://files.pythonhosted.org/packages/f7/3f/e21c6af55661e7499133245ab622871e375b716af5a96d83770f2ad6d602/llama_cpp_python-0.2.25.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.25
2024-02-28T07:53:54,256   Found link https://files.pythonhosted.org/packages/ce/64/16a6bbae31c24d07d1ef6f488b81d13e0eb009147f583d9047371216b7a0/llama_cpp_python-0.2.26.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.26
2024-02-28T07:53:54,257   Found link https://files.pythonhosted.org/packages/a9/83/e3b7405f36b2f3dd4ae76c32e9331232c5692078deda7f84c1f0ede071ab/llama_cpp_python-0.2.27.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.27
2024-02-28T07:53:54,258   Found link https://files.pythonhosted.org/packages/1b/7c/ebe6be46264fad03bf3490fdd48d03608c5e5f10656ffc0155f23b7872a9/llama_cpp_python-0.2.28.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.28
2024-02-28T07:53:54,259   Found link https://files.pythonhosted.org/packages/12/b6/91ec62d6b2b9648f013d77350446e0351b5685bd89129f188dae60157032/llama_cpp_python-0.2.29.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.29
2024-02-28T07:53:54,260   Found link https://files.pythonhosted.org/packages/04/fb/13c99d504497ab63833600f8ae2196e28c04ad2a1cb43987cc9b51dc0a56/llama_cpp_python-0.2.30.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.30
2024-02-28T07:53:54,261   Found link https://files.pythonhosted.org/packages/a1/c8/7831d0908b23670112663913b1789a7adb47dc70e28318ee889afc7fc3be/llama_cpp_python-0.2.31.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.31
2024-02-28T07:53:54,262   Found link https://files.pythonhosted.org/packages/80/65/01fd26598cdd3cd09b6ce006cca2290bb762a4cc9f76e1a2c9c5a00b8cff/llama_cpp_python-0.2.32.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.32
2024-02-28T07:53:54,263   Found link https://files.pythonhosted.org/packages/d4/5e/c544cd520169f55e6cad63d3b8dec9c4e47326b1cb4095a91dce942be1a7/llama_cpp_python-0.2.33.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.33
2024-02-28T07:53:54,263   Found link https://files.pythonhosted.org/packages/78/5f/d46a72081d6e0e77e44abf092b11517267e4d290a3f20cf3b9a9faab7705/llama_cpp_python-0.2.34.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.34
2024-02-28T07:53:54,264   Found link https://files.pythonhosted.org/packages/45/3e/c5eb7a5a2689c15657beb08d0c6915cc61a9a20311ff00a567fc7a70a530/llama_cpp_python-0.2.35.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.35
2024-02-28T07:53:54,265   Found link https://files.pythonhosted.org/packages/6a/25/02e865aee5472e28ec65ee0994ed9fce179ee106b41a9783e7e1816c557a/llama_cpp_python-0.2.36.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.36
2024-02-28T07:53:54,266   Found link https://files.pythonhosted.org/packages/ee/82/ce00de6b3b2adde8d59791ec986992b4e736da592cfafb22ccbdac14a049/llama_cpp_python-0.2.37.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.37
2024-02-28T07:53:54,267   Found link https://files.pythonhosted.org/packages/90/41/7774fb44546685c88193629f95e20adad3a3078a0bdb9aeacb174a6ee9ca/llama_cpp_python-0.2.38.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.38
2024-02-28T07:53:54,268   Found link https://files.pythonhosted.org/packages/af/a6/6b836876620823551650db19d217118b9ef0983a936aa7895ed5d05df9c0/llama_cpp_python-0.2.39.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.39
2024-02-28T07:53:54,269   Found link https://files.pythonhosted.org/packages/1a/d2/dbf69d882517a534c5640e7b7f1cca360882cbd53c8c5c25ff0a7a854e07/llama_cpp_python-0.2.40.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.40
2024-02-28T07:53:54,270   Found link https://files.pythonhosted.org/packages/35/73/b2abe489ae7a7fbe096266457a00a8f801b83c6929c9ee7a2fd0c43baff0/llama_cpp_python-0.2.41.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.41
2024-02-28T07:53:54,271   Found link https://files.pythonhosted.org/packages/71/71/d5acd94964c599b348e81714aac9e75a578f51d224ac0343e27e6d9c38fc/llama_cpp_python-0.2.42.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.42
2024-02-28T07:53:54,272   Found link https://files.pythonhosted.org/packages/2c/07/b2bbd5e826d5910be3fd96eb639ba717349b3c2b0cc1360b13c63c50338a/llama_cpp_python-0.2.43.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.43
2024-02-28T07:53:54,273   Found link https://files.pythonhosted.org/packages/a3/1d/fc000e07680831b074446f059611b02844fd9d949d70146b1ae7b2df9ccc/llama_cpp_python-0.2.44.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.44
2024-02-28T07:53:54,274   Found link https://files.pythonhosted.org/packages/7a/cb/3e958c169fabb2df7ffaeb170a5d2b2cc8370ff31621e23b778ebcd8ab24/llama_cpp_python-0.2.45.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.45
2024-02-28T07:53:54,275   Found link https://files.pythonhosted.org/packages/25/b0/1df28f6ec4d14432dddc56e04bb05c0e78c40bc5611c1a54132fe2244d1a/llama_cpp_python-0.2.46.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.46
2024-02-28T07:53:54,276   Found link https://files.pythonhosted.org/packages/b9/af/30371683d30a0485080448f0382ceec2272d1bce1a711904bb6a3cf3b38b/llama_cpp_python-0.2.47.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.47
2024-02-28T07:53:54,277   Found link https://files.pythonhosted.org/packages/2e/cf/ab532896aa3837755dca592962552ae5c9114b71590bee2d959c57e97710/llama_cpp_python-0.2.48.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.48
2024-02-28T07:53:54,278   Found link https://files.pythonhosted.org/packages/21/e9/71ceed04be64ca9ae36214ba94a8d271817ad83196af003db6435b9ca333/llama_cpp_python-0.2.49.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.49
2024-02-28T07:53:54,279   Found link https://files.pythonhosted.org/packages/e8/ff/492c54a6dde08db51fc4ae0b4c9f3e4c7bc5036eeab223ebdd51bc34a146/llama_cpp_python-0.2.50.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.50
2024-02-28T07:53:54,280   Found link https://files.pythonhosted.org/packages/9d/3a/5476da33c736830b73393f05851c8eccea6f5a54ec2a0e35fc1297d1b219/llama_cpp_python-0.2.51.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.51
2024-02-28T07:53:54,281   Found link https://files.pythonhosted.org/packages/4c/09/a1fefdac604d70b211918a0dbe47d65573368db8988a5fa4f0777e950f12/llama_cpp_python-0.2.52.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.52
2024-02-28T07:53:54,282   Found link https://files.pythonhosted.org/packages/61/a1/6a4f3df444ddd3903d07d35f3ef7a2a2f2711ced64944fd5ee3f0ed1ef39/llama_cpp_python-0.2.53.tar.gz (from https://pypi.org/simple/llama-cpp-python/) (requires-python:>=3.8), version: 0.2.53
2024-02-28T07:53:54,283 Fetching project page and analyzing links: https://www.piwheels.org/simple/llama-cpp-python/
2024-02-28T07:53:54,283 Getting page https://www.piwheels.org/simple/llama-cpp-python/
2024-02-28T07:53:54,285 Found index url https://www.piwheels.org/simple/
2024-02-28T07:53:54,714 Fetched page https://www.piwheels.org/simple/llama-cpp-python/ as text/html
2024-02-28T07:53:54,749   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.50-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=ae6213e1a296eb7773de5ace4c9709bb0c6c26b569f698401f02ec8c0b1f70e1 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,750   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.50-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=e64328caf961eb1349ba103303b224160d9ec1d905b360b8776f05ef8a56548c (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,750   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.49-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=7ee779b157b2285faa8f687ddfc37a70add93387f65c6d369c6f55af00e7991e (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,751   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.49-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=bebac0c1a654b69ac3ad5b033f47aefdf9c5cffaf561177fafd1f9137cd6a109 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,751   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.48-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=a770ff0c49d7b89225f276e004c0365dd2e2a29aade3813f181bf849bcfae172 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,752   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.48-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=44c1145db5af2f0e64f7dfeabbccad1b8a8f3f8191ac6d772942bc9707617774 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,752   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.44-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=bbed4880ea24c9048cd079bf375e248fcb287c58b4da1fa55db699f50498fc47 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,753   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.44-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=77f7353d0548dfc077df72accec9e446eb41d08531135f33e912e777f3709b7d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,754   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.43-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=74bf2edb0d26028c31a8ddb255ca8cbf09754f32f11ec4ba92b3c38f28c49689 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,754   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.43-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=902b3d68b16f3592a31bfab67f2743b6c880983d2388a86c794f1ff70dd0fbd5 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,755   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.42-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=0725254705f761711ae588c6ec374610b02c2be4fb42cef43c613f94b24e09fd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,755   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.42-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=eeb01d04e368a69d9e72b3f624bdb8e5ba1c7fd5bb05b867cb7db9aa2ecef712 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,756   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.41-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=605a1f8ad4a71ffaa08d9d81c061583f888c98daa92f90ae6702a0d132379ec5 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,757   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.41-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=b591c74c6abce1fb0130a7c5e1fcb00d995376bc5aa50bc57591cf3f0d78fcfd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,758   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.40-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=32e6eb85956ea95b1392b657da6eb22968aacb7fae0f1bf9d11c07cd4c2cef33 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,758   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.40-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=704761bc81d1deb8abe84f1a14ddc3cfc3d8d34ae64f74d4dfc6494552728619 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,759   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.39-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=150fa80b5bbf8b0d4e185d3f9dba6a0f955442d434c1aba5102d8813fff0e97b (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,759   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.39-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=48c95175d440fe2d7c0988c258ce439668b4c601e3fe03f7b1600fdec5f1c381 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,760   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.38-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=5f74ae2118cfc667cd8c6fae15341e0465f3aa5f607a4639c4cd20abcad4c0ef (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,760   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.38-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=5666d2bc6ca576a5b1db7ba9eb18f098f6dd45561e96ddc465ee68bb3242af7f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,761   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.37-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=52bf796d479f4e9df37e1828dabb987f8ce1d7c34bf968d86a08fac609b01d7d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,762   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.37-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=2c82f345afce240e7b7d385551145d1ce5ebab4461e943bb6024e4e9f9dffdf4 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,762   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.36-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=bb505332fcf1e70bfc1814f6159c487915a5df69dfab10907053a070e3b53449 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,763   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.36-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=eb2eabd471c1af5c77a8b7d69061e8f0dc3e56e10a5a6c4a77acd033f6183cd8 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,764   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.35-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=ab8f24a87f39bab7655d052963692ccd334b9eb78f2f2e9fb19d02616a6d647c (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,764   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.35-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=b49f9efa08a556a02732d0a22ed36e2e879ae2789ca9f10ec8ad9daf5c8b2f3f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,765   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.34-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=da6a7d8c431275720252bac217874d7eb9b8e97294e237c3053f01ba2659e611 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,765   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.34-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=b1389b56552f7b5a058bb447510394fe93e11aca6be95177dfdfd72ea58ef4d7 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,766   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.33-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=00eb7f4a087a39240cfc70aa2f1611a76ecc52c4c1d46e2b6fb8d88ea642bae3 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,766   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.33-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=96fff83d6f39dd9a71ea1da8da5bd4fe22561795a33d06b6cc01fdf0bff85ccf (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,767   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.32-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=7930ee195d390635aac4b7af0fd7cd490fc6f93e3922585e4cb156979b4e1660 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,767   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.32-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=78c4efbe665a8e60cc63cf23d37500de80fa88f33d62b4ee476a2957aecac4fa (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,768   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.31-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=fd6731ded8988f781e89c5a096a015772f9b4d8af17447ccb542030169c315c0 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,769   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.31-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=dd1044d26325193b7d26c03a05ba125774c659b32a2160bcb2763c1686aedab4 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,770   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.30-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=a58864e906f616d77145c2e9dd5cfc6e6db1ac219be004ff3f6b39c25a56a2a3 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,770   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.30-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=3cbff75b267c242ab801da2dc7e15a0fe32c029fa269e8628aff3469dade6e70 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,771   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.29-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=fc5f5cf3982532109d89e596be5659aece0c248a39a81bb5264fa0652d04d24e (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,772   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.29-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=04b881d5d2ce4e66256f858b4ac3ff037f96eb221d5bc558a73f4807bc2fd426 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,772   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.28-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=2c53b3e5679c7ee69fae7304e592e567dfd20adeaf161dada7a34fdb94b5fc5f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,773   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.27-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=02bd20ff69c48b49fedb4901900bc34e42031c1e155f14e077b61de5389a776d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,773   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.27-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=300e823a56d1ab95cfcbbca1a3dacc3217a9eadc208b203867b9f79e9ede9b89 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,774   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.26-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=ddca4eda48f63369879ef1bf209013469154af220d4c87677cba833316d255fb (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,775   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.26-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=8af06b93145405d9da8ec41db07fac77f9b7295b3da925d96b7cc360d135f9cd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,775   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.25-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=01d603b372965f4d2c44a69560535cbd9e1927f3a914f47b4aa5015a8fe2358a (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,776   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.25-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=89c1f7bd5208ad77af971a36a94812302a08e26d5c68dc5823dd56144600736d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,777   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.24-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=a10093f712345a2248e8b1b3516ab1683da2d5ea888bc2879d3a2c60d5d7f303 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,777   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.24-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=8a7693c022ebbcfa411231c816b64816996dcc6841d7d67301b115af9187d8a9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,778   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.23-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=8b3ce6db762da6790eb010227b523953e11bb6e2c38110ccdf57ec80a8609bb6 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,779   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.23-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=88148b8856335f05b52be26b07bc639db37be9e5162ecacdc481c0f1b658dcf1 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,779   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.22-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=d63553eca926a129319ccbc2f586b1a1cd3b5eb4aca1f18180142b3e3a27f72d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,780   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.22-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=11403337141805f35ae8325c881e9ce3741f2578f4cdb45b724a307dd635f829 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,781   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.20-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=da14ce17a2476a706a8e8b7489a303536550d7c8cdff9db42cb4b56985c7688f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,781   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.20-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=5e05d20b69f7e652531141ef60200d9351118692a28d8b87a8a8a7d527928e9a (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,782   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.19-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=c1833281926198d9276c3c08ac7cb0f49630c164ce8f29bab9c41e00d55e721f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,783   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.19-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=dd16bdc23237ef0e4cc1c9c4c29f6624c9b510052a3dfdaba483957289ac48d5 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,784   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_36_armv7l.whl#sha256=7f066f10c0560b76776560045941383e9b8627d7696362b387fd4e652db00dad (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,784   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_31_armv7l.whl#sha256=885911c08b103762c507be6075b91de5ecb5b5422f913d7b9f844dcf3ab9b6ae (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.8)
2024-02-28T07:53:54,785   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.57-cp37-cp37m-linux_armv6l.whl#sha256=c46f12906971196ab3fa8250c23e5ae1f72581c00d910fadf491a710a97cb3d7 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,785   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.57-cp37-cp37m-linux_armv7l.whl#sha256=c46f12906971196ab3fa8250c23e5ae1f72581c00d910fadf491a710a97cb3d7 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,786   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.57-cp39-cp39-linux_armv6l.whl#sha256=888f3796690ccb21c9fac07b1ff83afa7b56fedfaa70ce1568572f1b7fdb3f27 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,787   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.57-cp39-cp39-linux_armv7l.whl#sha256=888f3796690ccb21c9fac07b1ff83afa7b56fedfaa70ce1568572f1b7fdb3f27 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,787   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.57-cp311-cp311-linux_armv6l.whl#sha256=caf38ff85ab251e84b4f951438454931514bde01dc36643d034d340ed14736d9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,788   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.57-cp311-cp311-linux_armv7l.whl#sha256=caf38ff85ab251e84b4f951438454931514bde01dc36643d034d340ed14736d9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,788   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.56-cp37-cp37m-linux_armv6l.whl#sha256=6ca6e31293dbf909df09e8c0ff119a6706c3b279bbf05716bdd04e99b6ff1665 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,789   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.56-cp37-cp37m-linux_armv7l.whl#sha256=6ca6e31293dbf909df09e8c0ff119a6706c3b279bbf05716bdd04e99b6ff1665 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,790   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.56-cp39-cp39-linux_armv6l.whl#sha256=2e5b18a3b1b32ea7c1ec0205c6d65ab42b07e29da5bea6c6fc8d17cdd9ee22bd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,790   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.56-cp39-cp39-linux_armv7l.whl#sha256=2e5b18a3b1b32ea7c1ec0205c6d65ab42b07e29da5bea6c6fc8d17cdd9ee22bd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,791   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.55-cp39-cp39-linux_armv6l.whl#sha256=d9a4ec585cfc04a6b43e815fefdf6c493a08b569cace3fd7c9bbe4d2ebd97fc5 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,792   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.55-cp39-cp39-linux_armv7l.whl#sha256=d9a4ec585cfc04a6b43e815fefdf6c493a08b569cace3fd7c9bbe4d2ebd97fc5 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,792   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.55-cp37-cp37m-linux_armv6l.whl#sha256=edb85834fe2145fc906e933a5643471bdebf3f3e376675ab3e914785fd1ec21d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,793   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.55-cp37-cp37m-linux_armv7l.whl#sha256=edb85834fe2145fc906e933a5643471bdebf3f3e376675ab3e914785fd1ec21d (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,794   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.55-cp311-cp311-linux_armv6l.whl#sha256=6abbec187e6c40b192040ba4dee145ae69de4aaa65c3a350fe0cea85bf6aa197 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,795   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.55-cp311-cp311-linux_armv7l.whl#sha256=6abbec187e6c40b192040ba4dee145ae69de4aaa65c3a350fe0cea85bf6aa197 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,795   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.54-cp37-cp37m-linux_armv6l.whl#sha256=221d6012bf80f402d83593047359ddb7c767e83147d2c8445d24e58466b050bc (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,795   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.54-cp37-cp37m-linux_armv7l.whl#sha256=221d6012bf80f402d83593047359ddb7c767e83147d2c8445d24e58466b050bc (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,796   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.54-cp39-cp39-linux_armv6l.whl#sha256=064c3e8c4f3dd76aef301720241909048b2b4da4b0d1564b0436693e6efd1ddd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,796   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.54-cp39-cp39-linux_armv7l.whl#sha256=064c3e8c4f3dd76aef301720241909048b2b4da4b0d1564b0436693e6efd1ddd (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,797   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.54-cp311-cp311-linux_armv6l.whl#sha256=2552020ab6570979cc92527cce3acf131f181b466944034d0ae4bc4674934989 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,798   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.54-cp311-cp311-linux_armv7l.whl#sha256=2552020ab6570979cc92527cce3acf131f181b466944034d0ae4bc4674934989 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,798   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.53-cp37-cp37m-linux_armv6l.whl#sha256=b177a40248c14829c96942ccdc570d96cf86f94d2ccd1fba2440ca7f496432b1 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,799   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.53-cp37-cp37m-linux_armv7l.whl#sha256=b177a40248c14829c96942ccdc570d96cf86f94d2ccd1fba2440ca7f496432b1 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,800   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.53-cp39-cp39-linux_armv6l.whl#sha256=fb5ba2f1e57a03c0d0e587577ab280d1a4a4fed295f1fcd4e19a3313a2ef07ac (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,800   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.53-cp39-cp39-linux_armv7l.whl#sha256=fb5ba2f1e57a03c0d0e587577ab280d1a4a4fed295f1fcd4e19a3313a2ef07ac (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,801   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.53-cp311-cp311-linux_armv6l.whl#sha256=5afe359d7635ee4081bf60ef6cdbc35860b635d75699f7185b4d637c55ac2572 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,802   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.53-cp311-cp311-linux_armv7l.whl#sha256=5afe359d7635ee4081bf60ef6cdbc35860b635d75699f7185b4d637c55ac2572 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,802   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.52-cp37-cp37m-linux_armv6l.whl#sha256=bf3bc680532ad36080ca0e375cdb349c91ba90a6880c0c9090b83bb41463aacc (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,803   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.52-cp37-cp37m-linux_armv7l.whl#sha256=bf3bc680532ad36080ca0e375cdb349c91ba90a6880c0c9090b83bb41463aacc (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,803   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.52-cp39-cp39-linux_armv6l.whl#sha256=2d8f9447a21a804a90f8adcee77052587ab9ace32dbe36eca23c72cb2ce20fac (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,804   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.52-cp39-cp39-linux_armv7l.whl#sha256=2d8f9447a21a804a90f8adcee77052587ab9ace32dbe36eca23c72cb2ce20fac (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,804   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.52-cp311-cp311-linux_armv6l.whl#sha256=fefadcad700a08bdc860fb3a5f45f54d635e130484bbadf9015da2268f57cb44 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,805   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.52-cp311-cp311-linux_armv7l.whl#sha256=fefadcad700a08bdc860fb3a5f45f54d635e130484bbadf9015da2268f57cb44 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,805   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.51-cp37-cp37m-linux_armv6l.whl#sha256=23d1e81835a4f9d2cd07c25dfe46adb3541bc7e7104c92b9e4ce40d8042f40e0 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,806   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.51-cp37-cp37m-linux_armv7l.whl#sha256=23d1e81835a4f9d2cd07c25dfe46adb3541bc7e7104c92b9e4ce40d8042f40e0 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,806   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.51-cp39-cp39-linux_armv6l.whl#sha256=b7620dc9874978dd791e463c32bcd526f5eb3eb53b8b4221b9eaec21eabd7958 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,807   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.51-cp39-cp39-linux_armv7l.whl#sha256=b7620dc9874978dd791e463c32bcd526f5eb3eb53b8b4221b9eaec21eabd7958 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,808   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.51-cp311-cp311-linux_armv6l.whl#sha256=6b45a1fb53ff22631be2564cb7274fe170f2982b28a5476e8ff905770eec557e (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,808   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.51-cp311-cp311-linux_armv7l.whl#sha256=6b45a1fb53ff22631be2564cb7274fe170f2982b28a5476e8ff905770eec557e (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,809   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.50-cp37-cp37m-linux_armv6l.whl#sha256=5b64a8dc60df2396aa83907b89ccc8e6db4ab43e017b3b3a26c091714099da12 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,809   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.50-cp37-cp37m-linux_armv7l.whl#sha256=5b64a8dc60df2396aa83907b89ccc8e6db4ab43e017b3b3a26c091714099da12 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,810   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.50-cp311-cp311-linux_armv6l.whl#sha256=715122f66811a350122cd555ac8a883fd243f0008711c03138d76742162d1e63 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,810   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.50-cp311-cp311-linux_armv7l.whl#sha256=715122f66811a350122cd555ac8a883fd243f0008711c03138d76742162d1e63 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,811   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.49-cp37-cp37m-linux_armv6l.whl#sha256=6bb78e03dfe2c72307aede0cb78e223e8d69e29948c964f2a0651654c6d62d55 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,811   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.49-cp37-cp37m-linux_armv7l.whl#sha256=6bb78e03dfe2c72307aede0cb78e223e8d69e29948c964f2a0651654c6d62d55 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,812   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.48-cp37-cp37m-linux_armv6l.whl#sha256=67af3df96f6ba459ca0a542bf8ec23e3cafefef3b7f6ed6ec7fe5b2ac6be3a2f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,813   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.48-cp37-cp37m-linux_armv7l.whl#sha256=67af3df96f6ba459ca0a542bf8ec23e3cafefef3b7f6ed6ec7fe5b2ac6be3a2f (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,813   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.48-cp311-cp311-linux_armv6l.whl#sha256=7b4ce590d0f5b3f1b5c967a79a59067684631fb424510f80bed3f109f74a2d43 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,814   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.48-cp311-cp311-linux_armv7l.whl#sha256=7b4ce590d0f5b3f1b5c967a79a59067684631fb424510f80bed3f109f74a2d43 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,815   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.47-cp37-cp37m-linux_armv6l.whl#sha256=c4b404a9a588ba34c86302ea053359619a9aa93f844a933a08637cc65dfdb6e4 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,816   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.47-cp37-cp37m-linux_armv7l.whl#sha256=c4b404a9a588ba34c86302ea053359619a9aa93f844a933a08637cc65dfdb6e4 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,816   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.47-cp311-cp311-linux_armv6l.whl#sha256=a2ac92bd0de7e00a32f9fa9b5a1a22ead4031f5711ad81e191a2ebc8e9df3dcf (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,817   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.47-cp311-cp311-linux_armv7l.whl#sha256=a2ac92bd0de7e00a32f9fa9b5a1a22ead4031f5711ad81e191a2ebc8e9df3dcf (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,817   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.46-cp37-cp37m-linux_armv6l.whl#sha256=851936642b661501ebdd692b9cc1a9f420b54d4b6c1568a0b5561c0c313c3375 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,818   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.46-cp37-cp37m-linux_armv7l.whl#sha256=851936642b661501ebdd692b9cc1a9f420b54d4b6c1568a0b5561c0c313c3375 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,819   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.45-cp37-cp37m-linux_armv6l.whl#sha256=b01d7783f853028706cb7cd4833e1040430f089a3770cc4dcf88af128329b3e9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,820   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.45-cp37-cp37m-linux_armv7l.whl#sha256=b01d7783f853028706cb7cd4833e1040430f089a3770cc4dcf88af128329b3e9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,820   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.44-cp37-cp37m-linux_armv6l.whl#sha256=35dc305c6d40fbbc0ef489c18521a842192156419573134f83bfbb4ec4bfd3d9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,821   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.44-cp37-cp37m-linux_armv7l.whl#sha256=35dc305c6d40fbbc0ef489c18521a842192156419573134f83bfbb4ec4bfd3d9 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,822   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.43-cp37-cp37m-linux_armv6l.whl#sha256=49440356659a24d945119356b9c6e352e9dacf9e873e4d0d2167a501a7050592 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,822   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.43-cp37-cp37m-linux_armv7l.whl#sha256=49440356659a24d945119356b9c6e352e9dacf9e873e4d0d2167a501a7050592 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,823   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.42-cp37-cp37m-linux_armv6l.whl#sha256=48b89ad5d0e3274b6b637c58a8067672586596856f146a2e9c580c6f9ca285ef (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,824   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.42-cp37-cp37m-linux_armv7l.whl#sha256=48b89ad5d0e3274b6b637c58a8067672586596856f146a2e9c580c6f9ca285ef (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,824   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.41-cp37-cp37m-linux_armv6l.whl#sha256=eb37310c71596893c50ba3e1e2b45a236b54c86025f4e61e369e0e916e3ea927 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,825   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.41-cp37-cp37m-linux_armv7l.whl#sha256=eb37310c71596893c50ba3e1e2b45a236b54c86025f4e61e369e0e916e3ea927 (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,826   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.40-cp37-cp37m-linux_armv6l.whl#sha256=438062696c2aa9e624eba548d48c7e72e677f8514be6641dd76cad874124d08b (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,826   Skipping link: No binaries permitted for llama-cpp-python: https://www.piwheels.org/simple/llama-cpp-python/llama_cpp_python-0.1.40-cp37-cp37m-linux_armv7l.whl#sha256=438062696c2aa9e624eba548d48c7e72e677f8514be6641dd76cad874124d08b (from https://www.piwheels.org/simple/llama-cpp-python/) (requires-python:>=3.7)
2024-02-28T07:53:54,827 Skipping link: not a file: https://www.piwheels.org/simple/llama-cpp-python/
2024-02-28T07:53:54,828 Skipping link: not a file: https://pypi.org/simple/llama-cpp-python/
2024-02-28T07:53:54,862 Given no hashes to check 1 links for project 'llama-cpp-python': discarding no candidates
2024-02-28T07:53:54,881 Collecting llama-cpp-python==0.2.53
2024-02-28T07:53:54,883   Created temporary directory: /tmp/pip-unpack-vr4wtame
2024-02-28T07:53:55,171   Downloading llama_cpp_python-0.2.53.tar.gz (36.8 MB)
2024-02-28T07:54:03,916   Added llama-cpp-python==0.2.53 from https://files.pythonhosted.org/packages/61/a1/6a4f3df444ddd3903d07d35f3ef7a2a2f2711ced64944fd5ee3f0ed1ef39/llama_cpp_python-0.2.53.tar.gz to build tracker '/tmp/pip-build-tracker-tlab4r61'
2024-02-28T07:54:03,922   Created temporary directory: /tmp/pip-build-env-pgsw12_s
2024-02-28T07:54:03,926   Installing build dependencies: started
2024-02-28T07:54:03,927   Running command pip subprocess to install build dependencies
2024-02-28T07:54:05,090   Using pip 23.3.1 from /usr/local/lib/python3.11/dist-packages/pip (python 3.11)
2024-02-28T07:54:05,606   Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple
2024-02-28T07:54:06,403   Collecting scikit-build-core>=0.5.1 (from scikit-build-core[pyproject]>=0.5.1)
2024-02-28T07:54:06,427     Using cached https://www.piwheels.org/simple/scikit-build-core/scikit_build_core-0.8.1-py3-none-any.whl (139 kB)
2024-02-28T07:54:06,811   Collecting packaging>=20.9 (from scikit-build-core>=0.5.1->scikit-build-core[pyproject]>=0.5.1)
2024-02-28T07:54:06,829     Using cached https://www.piwheels.org/simple/packaging/packaging-23.2-py3-none-any.whl (53 kB)
2024-02-28T07:54:07,074   Collecting pathspec>=0.10.1 (from scikit-build-core[pyproject]>=0.5.1)
2024-02-28T07:54:07,091     Using cached https://www.piwheels.org/simple/pathspec/pathspec-0.12.1-py3-none-any.whl (31 kB)
2024-02-28T07:54:07,210   Collecting pyproject-metadata>=0.5 (from scikit-build-core[pyproject]>=0.5.1)
2024-02-28T07:54:07,227     Using cached https://www.piwheels.org/simple/pyproject-metadata/pyproject_metadata-0.7.1-py3-none-any.whl (7.4 kB)
2024-02-28T07:54:09,710   Installing collected packages: pathspec, packaging, scikit-build-core, pyproject-metadata
2024-02-28T07:54:10,424   Successfully installed packaging-23.2 pathspec-0.12.1 pyproject-metadata-0.7.1 scikit-build-core-0.8.1

2024-02-28T07:54:10,720   [notice] A new release of pip is available: 23.3.1 -> 24.0
2024-02-28T07:54:10,721   [notice] To update, run: python3 -m pip install --upgrade pip
2024-02-28T07:54:10,959   Installing build dependencies: finished with status 'done'
2024-02-28T07:54:10,962   Getting requirements to build wheel: started
2024-02-28T07:54:10,963   Running command Getting requirements to build wheel
2024-02-28T07:54:11,383   Getting requirements to build wheel: finished with status 'done'
2024-02-28T07:54:11,406   Created temporary directory: /tmp/pip-modern-metadata-60ls8a2g
2024-02-28T07:54:11,408   Preparing metadata (pyproject.toml): started
2024-02-28T07:54:11,409   Running command Preparing metadata (pyproject.toml)
2024-02-28T07:54:11,914   *** scikit-build-core 0.8.1 using CMake 3.25.1 (metadata_wheel)
2024-02-28T07:54:12,009   Preparing metadata (pyproject.toml): finished with status 'done'
2024-02-28T07:54:12,015   Source in /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617 has version 0.2.53, which satisfies requirement llama-cpp-python==0.2.53 from https://files.pythonhosted.org/packages/61/a1/6a4f3df444ddd3903d07d35f3ef7a2a2f2711ced64944fd5ee3f0ed1ef39/llama_cpp_python-0.2.53.tar.gz
2024-02-28T07:54:12,016   Removed llama-cpp-python==0.2.53 from https://files.pythonhosted.org/packages/61/a1/6a4f3df444ddd3903d07d35f3ef7a2a2f2711ced64944fd5ee3f0ed1ef39/llama_cpp_python-0.2.53.tar.gz from build tracker '/tmp/pip-build-tracker-tlab4r61'
2024-02-28T07:54:12,025 Created temporary directory: /tmp/pip-unpack-sotvvrlj
2024-02-28T07:54:12,026 Created temporary directory: /tmp/pip-unpack-i39gi_u0
2024-02-28T07:54:12,084 Building wheels for collected packages: llama-cpp-python
2024-02-28T07:54:12,088   Created temporary directory: /tmp/pip-wheel-gw0yl5zl
2024-02-28T07:54:12,089   Destination directory: /tmp/pip-wheel-gw0yl5zl
2024-02-28T07:54:12,091   Building wheel for llama-cpp-python (pyproject.toml): started
2024-02-28T07:54:12,092   Running command Building wheel for llama-cpp-python (pyproject.toml)
2024-02-28T07:54:12,588   *** scikit-build-core 0.8.1 using CMake 3.25.1 (wheel)
2024-02-28T07:54:12,607   *** Configuring CMake...
2024-02-28T07:54:12,701   loading initial cache file /tmp/tmp67mfmdk4/build/CMakeInit.txt
2024-02-28T07:54:12,975   -- The C compiler identification is GNU 12.2.0
2024-02-28T07:54:13,277   -- The CXX compiler identification is GNU 12.2.0
2024-02-28T07:54:13,327   -- Detecting C compiler ABI info
2024-02-28T07:54:13,586   -- Detecting C compiler ABI info - done
2024-02-28T07:54:13,642   -- Check for working C compiler: /usr/bin/cc - skipped
2024-02-28T07:54:13,645   -- Detecting C compile features
2024-02-28T07:54:13,648   -- Detecting C compile features - done
2024-02-28T07:54:13,672   -- Detecting CXX compiler ABI info
2024-02-28T07:54:13,990   -- Detecting CXX compiler ABI info - done
2024-02-28T07:54:14,028   -- Check for working CXX compiler: /usr/bin/c++ - skipped
2024-02-28T07:54:14,030   -- Detecting CXX compile features
2024-02-28T07:54:14,032   -- Detecting CXX compile features - done
2024-02-28T07:54:14,064   -- Found Git: /usr/bin/git (found version "2.39.2")
2024-02-28T07:54:14,115   -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
2024-02-28T07:54:14,413   -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
2024-02-28T07:54:14,420   -- Found Threads: TRUE
2024-02-28T07:54:14,432   -- Warning: ccache not found - consider installing it for faster compilation or disable this warning with LLAMA_CCACHE=OFF
2024-02-28T07:54:14,577   -- CMAKE_SYSTEM_PROCESSOR: armv7l
2024-02-28T07:54:14,578   -- ARM detected
2024-02-28T07:54:14,582   -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E
2024-02-28T07:54:14,897   -- Performing Test COMPILER_SUPPORTS_FP16_FORMAT_I3E - Success
2024-02-28T07:54:14,926   CMake Warning (dev) at CMakeLists.txt:21 (install):
2024-02-28T07:54:14,927     Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION.
2024-02-28T07:54:14,927   This warning is for project developers.  Use -Wno-dev to suppress it.

2024-02-28T07:54:14,928   CMake Warning (dev) at CMakeLists.txt:30 (install):
2024-02-28T07:54:14,928     Target llama has PUBLIC_HEADER files but no PUBLIC_HEADER DESTINATION.
2024-02-28T07:54:14,929   This warning is for project developers.  Use -Wno-dev to suppress it.

2024-02-28T07:54:14,935   -- Configuring done
2024-02-28T07:54:15,008   -- Generating done
2024-02-28T07:54:15,026   -- Build files have been written to: /tmp/tmp67mfmdk4/build
2024-02-28T07:54:15,038   *** Building project with Ninja...
2024-02-28T07:54:15,318   [1/22] cd /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp && /usr/bin/cmake -DMSVC= -DCMAKE_C_COMPILER_VERSION=12.2.0 -DCMAKE_C_COMPILER_ID=GNU -DCMAKE_VS_PLATFORM_NAME= -DCMAKE_C_COMPILER=/usr/bin/cc -P /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/../scripts/gen-build-info-cpp.cmake
2024-02-28T07:54:15,319   -- Found Git: /usr/bin/git (found version "2.39.2")
2024-02-28T07:54:15,533   [2/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600  -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/build_info.dir/build-info.cpp.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/build-info.cpp
2024-02-28T07:54:18,203   [3/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c
2024-02-28T07:54:18,204   FAILED: vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o
2024-02-28T07:54:18,205   /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-quants.c.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c
2024-02-28T07:54:18,206   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c: In function ‘ggml_vec_dot_iq2_s_q8_K’:
2024-02-28T07:54:18,207   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9668:32: error: implicit declaration of function ‘vld1q_u8_x2’; did you mean ‘vld1q_u32’? [-Werror=implicit-function-declaration]
2024-02-28T07:54:18,208    9668 |     const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
2024-02-28T07:54:18,209         |                                ^~~~~~~~~~~
2024-02-28T07:54:18,210         |                                vld1q_u32
2024-02-28T07:54:18,211   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9668:32: error: invalid initializer
2024-02-28T07:54:18,212   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9701:13: note: use ‘-flax-vector-conversions’ to permit conversions between vectors with differing element types or numbers of subparts
2024-02-28T07:54:18,213    9701 |             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
2024-02-28T07:54:18,214         |             ^~
2024-02-28T07:54:18,214   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9701:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,215    9701 |             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
2024-02-28T07:54:18,216         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,217         |                                  |
2024-02-28T07:54:18,218         |                                  int8x16_t
2024-02-28T07:54:18,219   In file included from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-impl.h:54,
2024-02-28T07:54:18,231                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.h:3,
2024-02-28T07:54:18,241                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:1:
2024-02-28T07:54:18,242   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,243   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,244         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,245   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9702:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,246    9702 |             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
2024-02-28T07:54:18,247         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,248         |                                  |
2024-02-28T07:54:18,249         |                                  int8x16_t
2024-02-28T07:54:18,250   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,251   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,252         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,253   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9710:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,254    9710 |             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
2024-02-28T07:54:18,255         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,256         |                                  |
2024-02-28T07:54:18,257         |                                  int8x16_t
2024-02-28T07:54:18,258   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,259   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,260         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,261   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:9711:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,262    9711 |             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
2024-02-28T07:54:18,263         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,263         |                                  |
2024-02-28T07:54:18,264         |                                  int8x16_t
2024-02-28T07:54:18,265   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,266   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,267         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,267   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c: In function ‘ggml_vec_dot_iq3_s_q8_K’:
2024-02-28T07:54:18,268   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:10006:32: error: invalid initializer
2024-02-28T07:54:18,269   10006 |     const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
2024-02-28T07:54:18,270         |                                ^~~~~~~~~~~
2024-02-28T07:54:18,271   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:10034:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,272   10034 |             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
2024-02-28T07:54:18,273         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,274         |                                  |
2024-02-28T07:54:18,275         |                                  int8x16_t
2024-02-28T07:54:18,276   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,291   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,292         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,293   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:10035:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,294   10035 |             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
2024-02-28T07:54:18,295         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,296         |                                  |
2024-02-28T07:54:18,297         |                                  int8x16_t
2024-02-28T07:54:18,297   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,298   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,299         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,300   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:10043:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,301   10043 |             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
2024-02-28T07:54:18,302         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,303         |                                  |
2024-02-28T07:54:18,304         |                                  int8x16_t
2024-02-28T07:54:18,305   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,306   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,307         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,308   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-quants.c:10044:34: error: incompatible type for argument 1 of ‘vandq_u8’
2024-02-28T07:54:18,309   10044 |             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
2024-02-28T07:54:18,310         |                                  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:18,310         |                                  |
2024-02-28T07:54:18,311         |                                  int8x16_t
2024-02-28T07:54:18,312   /usr/lib/gcc/arm-linux-gnueabihf/12/include/arm_neon.h:13874:22: note: expected ‘uint8x16_t’ but argument is of type ‘int8x16_t’
2024-02-28T07:54:18,313   13874 | vandq_u8 (uint8x16_t __a, uint8x16_t __b)
2024-02-28T07:54:18,314         |           ~~~~~~~~~~~^~~
2024-02-28T07:54:18,315   cc1: some warnings being treated as errors
2024-02-28T07:54:18,899   [4/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-alloc.c.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-alloc.c
2024-02-28T07:54:19,580   [5/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml-backend.c.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml-backend.c
2024-02-28T07:54:54,698   [6/22] /usr/bin/c++ -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/. -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -MF vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o.d -o vendor/llama.cpp/common/CMakeFiles/common.dir/common.cpp.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/common.cpp
2024-02-28T07:54:54,699   In file included from /usr/include/c++/12/vector:70,
2024-02-28T07:54:54,700                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/grammar-parser.h:14,
2024-02-28T07:54:54,701                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/sampling.h:5,
2024-02-28T07:54:54,702                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/common.h:7,
2024-02-28T07:54:54,702                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/common.cpp:1:
2024-02-28T07:54:54,703   /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const llama_model_kv_override&}; _Tp = llama_model_kv_override; _Alloc = std::allocator<llama_model_kv_override>]’:
2024-02-28T07:54:54,704   /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector<llama_model_kv_override>::iterator’ changed in GCC 7.1
2024-02-28T07:54:54,705     439 |       vector<_Tp, _Alloc>::
2024-02-28T07:54:54,705         |       ^~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:54,706   /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator<llama_model_kv_override>]’:
2024-02-28T07:54:54,707   /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector<llama_model_kv_override>::iterator’ changed in GCC 7.1
2024-02-28T07:54:54,707   In file included from /usr/include/c++/12/vector:64:
2024-02-28T07:54:54,708   In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = llama_model_kv_override; _Alloc = std::allocator<llama_model_kv_override>]’,
2024-02-28T07:54:54,709       inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/common.cpp:869:42:
2024-02-28T07:54:54,709   /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator<llama_model_kv_override*, std::vector<llama_model_kv_override> >’ changed in GCC 7.1
2024-02-28T07:54:54,710    1287 |           _M_realloc_insert(end(), __x);
2024-02-28T07:54:54,711         |           ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~
2024-02-28T07:54:54,711   In member function ‘void std::vector<_Tp, _Alloc>::emplace_back(_Args&& ...) [with _Args = {}; _Tp = llama_model_kv_override; _Alloc = std::allocator<llama_model_kv_override>]’,
2024-02-28T07:54:54,712       inlined from ‘bool gpt_params_parse_ex(int, char**, gpt_params&)’ at /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/common/common.cpp:914:41:
2024-02-28T07:54:54,713   /usr/include/c++/12/bits/vector.tcc:123:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator<llama_model_kv_override*, std::vector<llama_model_kv_override> >’ changed in GCC 7.1
2024-02-28T07:54:54,714     123 |           _M_realloc_insert(end(), std::forward<_Args>(__args)...);
2024-02-28T07:54:54,715         |           ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:54:59,651   [7/22] /usr/bin/cc -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu11 -MD -MT vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -MF vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o.d -o vendor/llama.cpp/CMakeFiles/ggml.dir/ggml.c.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/ggml.c
2024-02-28T07:55:54,085   [8/22] /usr/bin/c++ -DLLAMA_BUILD -DLLAMA_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dllama_EXPORTS -I/tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/. -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wno-format-truncation -Wextra-semi -mfp16-format=ieee -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations -std=gnu++11 -MD -MT vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -MF vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o.d -o vendor/llama.cpp/CMakeFiles/llama.dir/llama.cpp.o -c /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp
2024-02-28T07:55:54,086   In file included from /usr/include/c++/12/vector:64,
2024-02-28T07:55:54,087                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.h:984,
2024-02-28T07:55:54,087                    from /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:2:
2024-02-28T07:55:54,087   /usr/include/c++/12/bits/stl_vector.h: In function ‘std::vector<_Tp, _Alloc>::vector(std::initializer_list<_Tp>, const allocator_type&) [with _Tp = long long int; _Alloc = std::allocator<long long int>]’:
2024-02-28T07:55:54,088   /usr/include/c++/12/bits/stl_vector.h:673:7: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,088     673 |       vector(initializer_list<value_type> __l,
2024-02-28T07:55:54,089         |       ^~~~~~
2024-02-28T07:55:54,089   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp: In function ‘bool llm_load_tensors(llama_model_loader&, llama_model&, int, llama_split_mode, int, const float*, bool, llama_progress_callback, void*)’:
2024-02-28T07:55:54,090   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3821:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,090    3821 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,090         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,091   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3825:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,091    3825 |                         model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,092         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,092   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3827:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,093    3827 |                             model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,094         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,102   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3858:62: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,102    3858 |                             layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,103         |                                              ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,103   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3859:62: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,103    3859 |                             layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,104         |                                              ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,104   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3860:62: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,105    3860 |                             layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,106         |                                              ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,106   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3876:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,107    3876 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,107         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,107   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3878:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,108    3878 |                         model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,108         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,109   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3879:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,109    3879 |                         model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,110         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,110   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3888:59: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,111    3888 |                         layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,111         |                                           ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,111   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3890:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,112    3890 |                         layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,112         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,113   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3891:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,114    3891 |                         layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,114         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,115   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3892:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,115    3892 |                         layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,116         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,116   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3893:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,117    3893 |                         layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,117         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,118   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3895:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,118    3895 |                         layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,118         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,119   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3897:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,119    3897 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,119         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,120   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3898:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,121    3898 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,121         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,122   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3899:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,122    3899 |                         layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,123         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,123   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3904:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,124    3904 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,124         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,125   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3908:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,126    3908 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,126         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,127   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3909:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,128    3909 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,128         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,128   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3911:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,129    3911 |                             model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,     "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,129         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,130   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3913:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,130    3913 |                             model.output = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); // needs to be on GPU
2024-02-28T07:55:54,131         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,131   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3926:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,132    3926 |                         layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,132         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,133   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3929:67: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,133    3929 |                             layer.attn_norm_2   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "weight", i), {n_embd});
2024-02-28T07:55:54,134         |                                                   ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,134   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3930:67: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,135    3930 |                             layer.attn_norm_2_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM_2, "bias", i),   {n_embd});
2024-02-28T07:55:54,135         |                                                   ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,136   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3933:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,136    3933 |                         layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,136         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,137   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3937:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,138    3937 |                         layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,138         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,138   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3942:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,139    3942 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,139         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,140   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3943:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,140    3943 |                     model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD,   "weight"), {n_embd, hparams.n_ctx_train});
2024-02-28T07:55:54,140         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,141   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3947:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,142    3947 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,142         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,142   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3948:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,143    3948 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,143         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,144   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3949:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,144    3949 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,145         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,145   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3958:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,146    3958 |                         layer.attn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,146         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,147   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3961:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,147    3961 |                         layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,148         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,148   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3964:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,149    3964 |                         layer.wo   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,149         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,149   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3965:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,150    3965 |                         layer.bo   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd});
2024-02-28T07:55:54,150         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,151   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3968:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,151    3968 |                         layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,152         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,152   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3970:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,152    3970 |                         layer.ffn_down   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd});
2024-02-28T07:55:54,153         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,153   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3974:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,154    3974 |                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i),     {n_ff});
2024-02-28T07:55:54,154         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,155   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3979:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,155    3979 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"),  {n_embd, n_vocab});
2024-02-28T07:55:54,156         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,156   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3982:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,157    3982 |                         model.output_norm    = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,158         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,158   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3983:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,159    3983 |                         model.output_norm_b  = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,159         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,159   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3984:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,160    3984 |                         model.output         = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,160         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,161   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3993:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,161    3993 |                         layer.attn_norm     = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM,   "weight", i), {n_embd});
2024-02-28T07:55:54,162         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,162   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3994:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,162    3994 |                         layer.attn_norm_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM,   "bias",   i), {n_embd});
2024-02-28T07:55:54,163         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,163   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:3997:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,164    3997 |                         layer.bqkv          = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV,    "bias",   i), {n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,165         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,165   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4000:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,166    4000 |                         layer.bo            = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT,    "bias",   i), {n_embd});
2024-02-28T07:55:54,166         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,167   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4002:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,167    4002 |                         layer.ffn_down      = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN,    "weight", i), {n_ff, n_embd});
2024-02-28T07:55:54,168         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,169   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4003:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,169    4003 |                         layer.ffn_down_b    = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN,    "bias",   i), {n_embd});
2024-02-28T07:55:54,169         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,170   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4005:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,170    4005 |                         layer.ffn_up        = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,      "weight", i), {n_embd, n_ff});
2024-02-28T07:55:54,171         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,171   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4006:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,171    4006 |                         layer.ffn_up_b      = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,      "bias",   i), {n_ff});
2024-02-28T07:55:54,172         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,172   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4008:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,173    4008 |                         layer.ffn_norm      = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM,    "weight", i), {n_embd});
2024-02-28T07:55:54,173         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,174   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4009:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,174    4009 |                         layer.ffn_norm_b    = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM,    "bias",   i), {n_embd});
2024-02-28T07:55:54,174         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,175   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4012:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,175    4012 |                         layer.attn_q_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q_NORM, "bias",   i), {64});
2024-02-28T07:55:54,176         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,176   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4014:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,177    4014 |                         layer.attn_k_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {64});
2024-02-28T07:55:54,178         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,178   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4015:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,179    4015 |                         layer.attn_k_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K_NORM, "bias",   i), {64});
2024-02-28T07:55:54,179         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,180   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4021:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,180    4021 |                     model.tok_embd     = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD,  "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,180         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,181   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4022:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,181    4022 |                     model.type_embd    = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_vocab_type});
2024-02-28T07:55:54,182         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,182   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4024:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,183    4024 |                         model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD,    "weight"), {n_embd, hparams.n_ctx_train});
2024-02-28T07:55:54,183         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,184   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4027:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,184    4027 |                     model.tok_norm   = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,185         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,185   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4028:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,186    4028 |                     model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,186         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,187   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4037:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,187    4037 |                             layer.wq   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,188         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,188   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4038:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,189    4038 |                             layer.bq   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q,   "bias", i),   {n_embd});
2024-02-28T07:55:54,190         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,190   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4040:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,190    4040 |                             layer.wk   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,191         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,191   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4041:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,191    4041 |                             layer.bk   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K,   "bias", i),   {n_embd_gqa});
2024-02-28T07:55:54,192         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,192   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4043:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,193    4043 |                             layer.wv   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,193         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,194   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4044:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,194    4044 |                             layer.bv   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V,   "bias", i),   {n_embd_gqa});
2024-02-28T07:55:54,195         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,195   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4046:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,196    4046 |                             layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,196         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,197   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4049:65: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,197    4049 |                         layer.wo              = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT,      "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,198         |                                                 ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,198   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4051:65: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,199    4051 |                         layer.attn_out_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,200         |                                                 ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,200   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4052:65: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,200    4052 |                         layer.attn_out_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,201         |                                                 ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,201   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4054:65: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,201    4054 |                         layer.ffn_up          = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,        "weight", i), {n_embd, n_ff});
2024-02-28T07:55:54,202         |                                                 ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,202   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4055:65: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,203    4055 |                         layer.ffn_down        = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN,      "weight", i), {n_ff, n_embd});
2024-02-28T07:55:54,203         |                                                 ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,204   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4058:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,204    4058 |                             layer.bo         = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd});
2024-02-28T07:55:54,205         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,205   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4059:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,206    4059 |                             layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i),   {n_ff});
2024-02-28T07:55:54,206         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,207   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4061:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,207    4061 |                             layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i),   {n_embd});
2024-02-28T07:55:54,208         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,208   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4063:64: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,209    4063 |                             layer.ffn_gate   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,209         |                                                ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,210   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4066:66: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,210    4066 |                         layer.layer_out_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_LAYER_OUT_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,211         |                                                  ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,211   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4067:66: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,211    4067 |                         layer.layer_out_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_LAYER_OUT_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,212         |                                                  ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,212   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4072:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,212    4072 |                     model.tok_embd   = ml.create_tensor(ctx_input,  tn(LLM_TENSOR_TOKEN_EMBD,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,213         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,213   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4073:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,214    4073 |                     model.tok_norm   = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,214         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,216   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4074:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,217    4074 |                     model.tok_norm_b = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,217         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,218   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4078:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,219    4078 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,219         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,220   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4079:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,220    4079 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,221         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,222   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4080:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,223    4080 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,223         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,224   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4089:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,224    4089 |                         layer.attn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,225         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,226   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4090:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,226    4090 |                         layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,227         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,227   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4093:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,228    4093 |                         layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i),   {n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,228         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,229   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4095:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,229    4095 |                         layer.wo   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,230         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,231   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4096:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,231    4096 |                         layer.bo   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd});
2024-02-28T07:55:54,232         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,232   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4099:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,233    4099 |                         layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,233         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,234   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4101:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,234    4101 |                         layer.ffn_down   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd});
2024-02-28T07:55:54,235         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,236   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4102:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,236    4102 |                         layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i),   {n_embd});
2024-02-28T07:55:54,237         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,237   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4104:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,238    4104 |                         layer.ffn_up     = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd, n_ff});
2024-02-28T07:55:54,238         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,239   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4105:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,240    4105 |                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i),   {n_ff});
2024-02-28T07:55:54,240         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,241   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4110:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,242    4110 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,242         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,243   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4114:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,243    4114 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,244         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,244   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4115:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,245    4115 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd}, false);
2024-02-28T07:55:54,245         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,246   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4118:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,246    4118 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_TOKEN_EMBD,  "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,247         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,247   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4129:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,248    4129 |                         layer.attn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,248         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,249   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4130:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,249    4130 |                         layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i),   {n_embd}, false);
2024-02-28T07:55:54,250         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,250   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4132:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,250    4132 |                         layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,251         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,251   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4133:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,252    4133 |                         layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i),   {n_embd + 2*n_embd_gqa}, false);
2024-02-28T07:55:54,252         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,253   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4135:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,253    4135 |                         layer.wo   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,254         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,254   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4136:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,255    4136 |                         layer.bo   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd}, false);
2024-02-28T07:55:54,255         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,256   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4138:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,256    4138 |                         layer.ffn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,257         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,257   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4142:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,258    4142 |                         layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i),   {n_embd}, false);
2024-02-28T07:55:54,258         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,258   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4145:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,259    4145 |                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i),   {n_ff}, false);
2024-02-28T07:55:54,259         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,260   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4148:57: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,260    4148 |                         layer.ffn_act = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_ACT, "scales", i), {n_ff}, false);
2024-02-28T07:55:54,261         |                                         ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,261   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4153:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,262    4153 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,263         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,264   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4157:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,264    4157 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,265         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,266   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4158:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,267    4158 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,267         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,268   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4159:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,269    4159 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,270         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,271   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4168:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,272    4168 |                         layer.attn_norm =   ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,272         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,273   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4173:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,274    4173 |                         layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,274         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,275   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4177:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,276    4177 |                         layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd},     false);
2024-02-28T07:55:54,277         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,277   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4178:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,278    4178 |                         layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_gqa}, false);
2024-02-28T07:55:54,279         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,279   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4179:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,280    4179 |                         layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_gqa}, false);
2024-02-28T07:55:54,281         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,282   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4181:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,283    4181 |                         layer.ffn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,284         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,285   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4182:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,286    4182 |                         layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,287         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,287   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4184:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,288    4184 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,289         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,290   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4185:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,291    4185 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,292         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,292   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4186:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,293    4186 |                         layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,294         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,294   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4191:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,295    4191 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,296         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,297   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4195:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,298    4195 |                         model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,299         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,300   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4196:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,301    4196 |                         model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,302         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,302   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4205:59: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,303    4205 |                         layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,304         |                                           ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,305   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4207:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,305    4207 |                         layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd*3});
2024-02-28T07:55:54,306         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,307   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4213:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,308    4213 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff/2});
2024-02-28T07:55:54,308         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,309   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4214:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,309    4214 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff/2, n_embd});
2024-02-28T07:55:54,310         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,311   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4220:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,311    4220 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,312         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,312   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4224:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,313    4224 |                         model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,314         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,315   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4225:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,316    4225 |                         model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,317         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,318   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4236:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,319    4236 |                         layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,320         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,321   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4237:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,321    4237 |                         layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,322         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,323   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4238:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,324    4238 |                         layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,325         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,325   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4243:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,326    4243 |                         layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_gqa});
2024-02-28T07:55:54,327         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,327   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4244:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,328    4244 |                         layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_gqa});
2024-02-28T07:55:54,328         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,329   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4249:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,330    4249 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,330         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,331   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4250:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,332    4250 |                         layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,333         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,334   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4255:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,335    4255 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,335         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,336   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4259:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,336    4259 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,337         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,337   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4260:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,338    4260 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,338         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,339   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4261:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,339    4261 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,340         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,340   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4262:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,340    4262 |                         model.output_b      = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT,      "bias"),   {n_vocab});
2024-02-28T07:55:54,341         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,341   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4272:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,342    4272 |                         layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,342         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,342   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4274:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,343    4274 |                         layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, false);
2024-02-28T07:55:54,343         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,344   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4275:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,344    4275 |                         layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i),   {n_embd + 2*n_embd_gqa}, false);
2024-02-28T07:55:54,345         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,345   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4278:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,346    4278 |                             layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,346         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,347   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4279:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,347    4279 |                             layer.bq = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_Q, "bias", i),   {n_embd});
2024-02-28T07:55:54,348         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,349   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4281:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,349    4281 |                             layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K, "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,350         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,350   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4282:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,350    4282 |                             layer.bk = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_K, "bias", i),   {n_embd_gqa});
2024-02-28T07:55:54,351         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,351   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4284:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,352    4284 |                             layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,352         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,352   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4285:56: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,353    4285 |                             layer.bv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_V, "bias", i),   {n_embd_gqa});
2024-02-28T07:55:54,353         |                                        ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,354   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4289:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,354    4289 |                         layer.bo   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd});
2024-02-28T07:55:54,355         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,355   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4291:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,355    4291 |                         layer.ffn_down   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd});
2024-02-28T07:55:54,356         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,356   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4292:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,357    4292 |                         layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i),   {n_embd});
2024-02-28T07:55:54,357         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,358   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4294:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,359    4294 |                         layer.ffn_up     = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd, n_ff});
2024-02-28T07:55:54,359         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,360   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4295:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,360    4295 |                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i),   {n_ff});
2024-02-28T07:55:54,360         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,361   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4300:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,361    4300 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,362         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,362   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4304:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,362    4304 |                         model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,363         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,363   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4305:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,364    4305 |                         model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,364         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,365   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4314:59: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,366    4314 |                         layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,366         |                                           ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,367   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4316:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,367    4316 |                         layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,368         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,368   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4317:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,369    4317 |                         layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,372         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,373   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4318:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,373    4318 |                         layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,374         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,374   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4319:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,375    4319 |                         layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,375         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,376   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4321:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,376    4321 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,376         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,377   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4322:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,377    4322 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,378         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,378   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4323:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,379    4323 |                         layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,380         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,380   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4328:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,381    4328 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,381         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,382   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4329:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,382    4329 |                     model.pos_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_POS_EMBD,   "weight"),   {n_embd, hparams.n_ctx_train});
2024-02-28T07:55:54,383         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,384   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4333:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,384    4333 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,384         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,385   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4334:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,385    4334 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,385         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,386   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4335:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,386    4335 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,387         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,387   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4344:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,388    4344 |                         layer.attn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM,   "weight", i), {n_embd});
2024-02-28T07:55:54,388         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,389   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4347:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,389    4347 |                         layer.wqkv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,390         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,390   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4348:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,391    4348 |                         layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i),   {n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,391         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,392   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4350:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,392    4350 |                         layer.wo   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,393         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,393   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4351:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,394    4351 |                         layer.bo   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd});
2024-02-28T07:55:54,394         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,394   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4353:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,395    4353 |                         layer.ffn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,395         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,395   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4354:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,396    4354 |                         layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,396         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,397   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4356:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,397    4356 |                         layer.ffn_down   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd});
2024-02-28T07:55:54,398         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,398   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4360:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,399    4360 |                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP,   "bias", i),   {n_ff});
2024-02-28T07:55:54,400         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,400   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4365:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,401    4365 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,401         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,402   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4369:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,402    4369 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,403         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,403   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4370:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,404    4370 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,404         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,405   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4371:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,405    4371 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,405         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,406   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4380:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,406    4380 |                         layer.attn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,407         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,407   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4381:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,407    4381 |                         layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,408         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,409   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4384:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,409    4384 |                         layer.bqkv = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_QKV, "bias", i),   {n_embd + 2*n_embd_gqa});
2024-02-28T07:55:54,410         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,410   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4386:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,411    4386 |                         layer.wo   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,411         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,412   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4387:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,412    4387 |                         layer.bo   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_OUT, "bias", i),   {n_embd});
2024-02-28T07:55:54,413         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,413   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4389:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,414    4389 |                         layer.ffn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,415         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,415   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4390:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,415    4390 |                         layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,416         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,416   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4393:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,416    4393 |                         layer.ffn_down_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_DOWN, "bias", i),   {n_embd});
2024-02-28T07:55:54,417         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,417   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4395:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,418    4395 |                         layer.ffn_up     = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP, "weight", i),   {n_embd, n_ff});
2024-02-28T07:55:54,418         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,418   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4396:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,419    4396 |                         layer.ffn_up_b   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_UP, "bias", i),     {n_ff});
2024-02-28T07:55:54,420         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,420   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4401:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,421    4401 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,421         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,422   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4403:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,422    4403 |                         model.output_norm   = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,423         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,423   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4404:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,424    4404 |                         model.output_norm_b = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "bias"),   {n_embd});
2024-02-28T07:55:54,424         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,425   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4405:63: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,426    4405 |                         model.output        = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,426         |                                               ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,426   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4413:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,427    4413 |                         layer.attn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,427         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,427   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4416:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,428    4416 |                         layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,428         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,429   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4419:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,429    4419 |                         layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,430         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,431   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4421:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,431    4421 |                         layer.ffn_norm   = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,432         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,432   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4422:60: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,433    4422 |                         layer.ffn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "bias", i),   {n_embd});
2024-02-28T07:55:54,433         |                                            ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,434   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4424:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,434    4424 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,434         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,435   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4425:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,435    4425 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,436         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,437   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4431:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,437    4431 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,437         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,438   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4435:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,438    4435 |                         model.output_norm = ml.create_tensor(ctx_output,       tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,438         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,439   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4436:61: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,439    4436 |                         model.output      = ml.create_tensor(ctx_output_split, tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,440         |                                             ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,440   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4445:59: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,441    4445 |                         layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,441         |                                           ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,442   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4447:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,442    4447 |                         layer.wq = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_Q,   "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,443         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,443   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4448:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,444    4448 |                         layer.wk = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_K,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,444         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,445   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4449:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,445    4449 |                         layer.wv = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_V,   "weight", i), {n_embd, n_embd_gqa});
2024-02-28T07:55:54,446         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,446   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4451:52: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,447    4451 |                         layer.wo = ml.create_tensor(ctx_split, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd});
2024-02-28T07:55:54,447         |                                    ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,447   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4452:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,448    4452 |                         layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
2024-02-28T07:55:54,448         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,449   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4453:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,449    4453 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,450         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,450   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4454:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,451    4454 |                         layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  n_ff, n_embd});
2024-02-28T07:55:54,451         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,452   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4460:54: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,452    4460 |                     model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
2024-02-28T07:55:54,453         |                                      ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,454   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4463:57: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,454    4463 |                     model.output_norm = ml.create_tensor(ctx_output, tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd});
2024-02-28T07:55:54,455         |                                         ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,455   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4464:57: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,455    4464 |                     model.output      = ml.create_tensor(ctx_output, tn(LLM_TENSOR_TOKEN_EMBD,  "weight"), {n_embd, n_vocab}); // same as tok_embd, duplicated to allow offloading
2024-02-28T07:55:54,456         |                                         ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,457   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4487:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,457    4487 |                         layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,458         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,458   /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617/vendor/llama.cpp/llama.cpp:4488:58: note: parameter passing for argument of type ‘std::initializer_list<long long int>’ changed in GCC 7.1
2024-02-28T07:55:54,458    4488 |                         layer.ffn_up   = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   n_ff});
2024-02-28T07:55:54,459         |                                          ~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,459   In file included from /usr/include/c++/12/vector:70:
2024-02-28T07:55:54,459   /usr/include/c++/12/bits/vector.tcc: In member function ‘void std::vector<_Tp, _Alloc>::_M_realloc_insert(iterator, _Args&& ...) [with _Args = {const double&}; _Tp = double; _Alloc = std::allocator<double>]’:
2024-02-28T07:55:54,460   /usr/include/c++/12/bits/vector.tcc:439:7: note: parameter passing for argument of type ‘std::vector<double>::iterator’ changed in GCC 7.1
2024-02-28T07:55:54,460     439 |       vector<_Tp, _Alloc>::
2024-02-28T07:55:54,461         |       ^~~~~~~~~~~~~~~~~~~
2024-02-28T07:55:54,461   In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator<double>]’,
2024-02-28T07:55:54,462       inlined from ‘std::back_insert_iterator<_Container>& std::back_insert_iterator<_Container>::operator=(const typename _Container::value_type&) [with _Container = std::vector<double>]’ at /usr/include/c++/12/bits/stl_iterator.h:735:22,
2024-02-28T07:55:54,462       inlined from ‘_OutputIterator std::partial_sum(_InputIterator, _InputIterator, _OutputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator<double*, vector<double> >; _OutputIterator = back_insert_iterator<vector<double> >]’ at /usr/include/c++/12/bits/stl_numeric.h:270:17,
2024-02-28T07:55:54,463       inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23:
2024-02-28T07:55:54,463   /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator<double*, std::vector<double> >’ changed in GCC 7.1
2024-02-28T07:55:54,464    1287 |           _M_realloc_insert(end(), __x);
2024-02-28T07:55:54,464         |           ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~
2024-02-28T07:55:54,465   In member function ‘void std::vector<_Tp, _Alloc>::push_back(const value_type&) [with _Tp = double; _Alloc = std::allocator<double>]’,
2024-02-28T07:55:54,465       inlined from ‘std::back_insert_iterator<_Container>& std::back_insert_iterator<_Container>::operator=(const typename _Container::value_type&) [with _Container = std::vector<double>]’ at /usr/include/c++/12/bits/stl_iterator.h:735:22,
2024-02-28T07:55:54,466       inlined from ‘_OutputIterator std::partial_sum(_InputIterator, _InputIterator, _OutputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator<double*, vector<double> >; _OutputIterator = back_insert_iterator<vector<double> >]’ at /usr/include/c++/12/bits/stl_numeric.h:274:16,
2024-02-28T07:55:54,466       inlined from ‘void std::discrete_distribution<_IntType>::param_type::_M_initialize() [with _IntType = int]’ at /usr/include/c++/12/bits/random.tcc:2679:23:
2024-02-28T07:55:54,467   /usr/include/c++/12/bits/stl_vector.h:1287:28: note: parameter passing for argument of type ‘__gnu_cxx::__normal_iterator<double*, std::vector<double> >’ changed in GCC 7.1
2024-02-28T07:55:54,467    1287 |           _M_realloc_insert(end(), __x);
2024-02-28T07:55:54,468         |           ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~
2024-02-28T07:55:54,468   ninja: build stopped: subcommand failed.

2024-02-28T07:55:54,469   *** CMake build failed
2024-02-28T07:55:54,470   ERROR: Building wheel for llama-cpp-python (pyproject.toml) exited with 1
2024-02-28T07:55:54,484   [bold magenta]full command[/]: [blue]/usr/bin/python3 /usr/local/lib/python3.11/dist-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py build_wheel /tmp/tmpgcqw2vop[/]
2024-02-28T07:55:54,484   [bold magenta]cwd[/]: /tmp/pip-wheel-1e0qhhza/llama-cpp-python_5906e59816184d0d863e6ff77b057617
2024-02-28T07:55:54,485   Building wheel for llama-cpp-python (pyproject.toml): finished with status 'error'
2024-02-28T07:55:54,487   ERROR: Failed building wheel for llama-cpp-python
2024-02-28T07:55:54,490 Failed to build llama-cpp-python
2024-02-28T07:55:54,491 ERROR: Failed to build one or more wheels
2024-02-28T07:55:54,492 Exception information:
2024-02-28T07:55:54,492 Traceback (most recent call last):
2024-02-28T07:55:54,492   File "/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/base_command.py", line 180, in exc_logging_wrapper
2024-02-28T07:55:54,492     status = run_func(*args)
2024-02-28T07:55:54,492              ^^^^^^^^^^^^^^^
2024-02-28T07:55:54,492   File "/usr/local/lib/python3.11/dist-packages/pip/_internal/cli/req_command.py", line 245, in wrapper
2024-02-28T07:55:54,492     return func(self, options, args)
2024-02-28T07:55:54,492            ^^^^^^^^^^^^^^^^^^^^^^^^^
2024-02-28T07:55:54,492   File "/usr/local/lib/python3.11/dist-packages/pip/_internal/commands/wheel.py", line 181, in run
2024-02-28T07:55:54,492     raise CommandError("Failed to build one or more wheels")
2024-02-28T07:55:54,492 pip._internal.exceptions.CommandError: Failed to build one or more wheels
2024-02-28T07:55:54,496 Removed build tracker: '/tmp/pip-build-tracker-tlab4r61'