python3 cli_demo.py chatglm 和 python web_demo.py chatglm部署遇到问题

[ou-jiajian]

python3 cli_demo.py chatglm
[i 0121 11:52:21.719398 00 compiler.py:956] Jittor(1.3.8.5) src: /opt/homebrew/lib/python3.11/site-packages/jittor
[i 0121 11:52:21.737304 00 compiler.py:957] clang at /usr/bin/clang++(15.0.0)
[i 0121 11:52:21.737433 00 compiler.py:958] cache_path: /Users/oujiajian/.cache/jittor/jt1.3.8/clang15.0.0/py3.11.7/macOS-14.2.1-axac/AppleM1/master
[i 0121 11:52:22.064102 00 init.py:227] Total mem: 16.00GB, using 5 procs for compiling.
[i 0121 11:52:22.234178 00 jit_compiler.cc:28] Load cc_path: /usr/bin/clang++
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 62%|██████████████████████████████████████████████████████████████████████████▍ | 5/8 [00:09<00:05, 1.92s/it]
Traceback (most recent call last):
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 415, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/torch/serialization.py", line 993, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/torch/serialization.py", line 447, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 419, in load_state_dict
if f.read(7) == "version":
^^^^^^^^^
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/oujiajian/JittorLLMs/cli_demo.py", line 8, in
model = models.get_model(args)
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/oujiajian/JittorLLMs/models/init.py", line 49, in get_model
return module.get_model(args)
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/oujiajian/JittorLLMs/models/chatglm/init.py", line 48, in get_model
return ChatGLMMdoel(args)
^^^^^^^^^^^^^^^^^^
File "/Users/oujiajian/JittorLLMs/models/chatglm/init.py", line 22, in init
self.model = AutoModel.from_pretrained(os.path.dirname(file), trust_remote_code=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 459, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2478, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2780, in _load_pretrained_model
state_dict = load_state_dict(shard_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 431, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for '/Users/oujiajian/JittorLLMs/models/chatglm/pytorch_model-00006-of-00008.bin' at '/Users/oujiajian/JittorLLMs/models/chatglm/pytorch_model-00006-of-00008.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

python3 web_demo.py chatglm
[i 0121 11:50:56.830004 00 compiler.py:956] Jittor(1.3.8.5) src: /opt/homebrew/lib/python3.11/site-packages/jittor
[i 0121 11:50:56.847275 00 compiler.py:957] clang at /usr/bin/clang++(15.0.0)
[i 0121 11:50:56.847352 00 compiler.py:958] cache_path: /Users/oujiajian/.cache/jittor/jt1.3.8/clang15.0.0/py3.11.7/macOS-14.2.1-axac/AppleM1/master
[i 0121 11:50:57.183703 00 init.py:227] Total mem: 16.00GB, using 5 procs for compiling.
[i 0121 11:50:57.339595 00 jit_compiler.cc:28] Load cc_path: /usr/bin/clang++
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 62%|██████████████████████████████████████████████████████████████████████████▍ | 5/8 [00:08<00:05, 1.80s/it]
Traceback (most recent call last):
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 415, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/torch/serialization.py", line 993, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/torch/serialization.py", line 447, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 419, in load_state_dict
if f.read(7) == "version":
^^^^^^^^^
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/oujiajian/JittorLLMs/web_demo.py", line 26, in
model = models.get_model(args)
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/oujiajian/JittorLLMs/models/init.py", line 49, in get_model
return module.get_model(args)
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/oujiajian/JittorLLMs/models/chatglm/init.py", line 48, in get_model
return ChatGLMMdoel(args)
^^^^^^^^^^^^^^^^^^
File "/Users/oujiajian/JittorLLMs/models/chatglm/init.py", line 22, in init
self.model = AutoModel.from_pretrained(os.path.dirname(file), trust_remote_code=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 459, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2478, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 2780, in _load_pretrained_model
state_dict = load_state_dict(shard_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/homebrew/lib/python3.11/site-packages/transformers/modeling_utils.py", line 431, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for '/Users/oujiajian/JittorLLMs/models/chatglm/pytorch_model-00006-of-00008.bin' at '/Users/oujiajian/JittorLLMs/models/chatglm/pytorch_model-00006-of-00008.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

MacBook Pro M1芯片 16G
好像都是同一个问题，到底该怎么解决？

[huongyj]

试试去安装路径下把这个6号文件删了再重新走一遍？
'/Users/oujiajian/JittorLLMs/models/chatglm/pytorch_model-00006-of-00008.bin'