René's URL Explorer Experiment

{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"python3 convert-hf-to-ggml.py bigcode/starcoderplus is failing with error: RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory","articleBody":"python3 convert-hf-to-ggml.py bigcode/starcoderplus \r\n\r\nis failing with error: RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory\r\n\r\n```\r\n% python3 convert-hf-to-ggml.py models/starcoderplus\r\nLoading model:  models/starcoderplus\r\nLoading checkpoint shards:  29%|█████████████████████████████████████▍                                                                                             | 2/7 [00:45\u003c01:54, 22.80s/it]\r\nTraceback (most recent call last):\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py\", line 460, in load_state_dict\r\n    return torch.load(checkpoint_file, map_location=\"cpu\")\r\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/torch/serialization.py\", line 797, in load\r\n    with _open_zipfile_reader(opened_file) as opened_zipfile:\r\n         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/torch/serialization.py\", line 283, in __init__\r\n    super().__init__(torch._C.PyTorchFileReader(name_or_buffer))\r\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\nRuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory\r\n\r\nDuring handling of the above exception, another exception occurred:\r\n\r\nTraceback (most recent call last):\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py\", line 464, in load_state_dict\r\n    if f.read(7) == \"version\":\r\n       ^^^^^^^^^\r\n  File \"\u003cfrozen codecs\u003e\", line 322, in decode\r\nUnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 128: invalid start byte\r\n\r\nDuring handling of the above exception, another exception occurred:\r\n\r\nTraceback (most recent call last):\r\n  File \"/starcoder.cpp/convert-hf-to-ggml.py\", line 58, in \u003cmodule\u003e\r\n    model = AutoModelForCausalLM.from_pretrained(model_name, config=config, torch_dtype=torch.float16 if use_f16 else torch.float32, low_cpu_mem_usage=True, trust_remote_code=True, offload_state_dict=True)\r\n            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py\", line 493, in from_pretrained\r\n    return model_class.from_pretrained(\r\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py\", line 2903, in from_pretrained\r\n    ) = cls._load_pretrained_model(\r\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py\", line 3246, in _load_pretrained_model\r\n    state_dict = load_state_dict(shard_file)\r\n                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^\r\n  File \"/starcoder.cpp/venv/lib/python3.11/site-packages/transformers/modeling_utils.py\", line 476, in load_state_dict\r\n    raise OSError(\r\nOSError: Unable to load weights from pytorch checkpoint file for 'models/starcoderplus/pytorch_model-00003-of-00007.bin' at 'models/starcoderplus/pytorch_model-00003-of-00007.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.\r\n```\r\n\r\nInstalled python packages:\r\n\r\n```\r\n% pip3 list                                         \r\nPackage            Version\r\n------------------ ---------\r\naccelerate         0.21.0\r\ncertifi            2023.7.22\r\ncharset-normalizer 3.2.0\r\nfilelock           3.12.2\r\nfsspec             2023.6.0\r\nhuggingface        0.0.1\r\nhuggingface-hub    0.16.4\r\nidna               3.4\r\nJinja2             3.1.2\r\nMarkupSafe         2.1.3\r\nmpmath             1.3.0\r\nnetworkx           3.1\r\nnumpy              1.25.1\r\npackaging          23.1\r\npip                23.0.1\r\npsutil             5.9.5\r\nPyYAML             6.0.1\r\nregex              2023.6.3\r\nrequests           2.31.0\r\nsafetensors        0.3.1\r\nsetuptools         67.6.1\r\nstarcoder          0.0.2\r\nsympy              1.12\r\ntokenizers         0.13.3\r\ntorch              2.0.1\r\ntqdm               4.65.0\r\ntransformers       4.31.0\r\ntyping_extensions  4.7.1\r\nurllib3            2.0.4\r\n```\r\n\r\n","author":{"url":"https://github.com/antonakv","@type":"Person","name":"antonakv"},"datePublished":"2023-07-24T10:05:52.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":1},"url":"https://github.com/29/starcoder.cpp/issues/29"}