Missing Model Files?

#1
by zengliangcs - opened

It seems that the model files from model-00001-of-00014.safetensors to model-00003-of-00014.safetensors might be missing. Could you please confirm?

SWE-bench org

Oh what the heck, not sure how that happened. Just uploaded. Thanks for the catch!

john-b-yang changed discussion status to closed

The model-00004-of-00014.safetensors file seems too small. You should double-check whether the model files were uploaded completely and whether they can be loaded correctly.

SWE-bench org

Yeah good catch - I think the previous upload I did early-terminated. Just did it again, and double checked pulling + inference, it's good to go now!

>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> model = AutoModelForCausalLM.from_pretrained("/mnt/data/liang.zeng/models/SWE-agent-LM-32B")
[2025-05-08 14:06:00,311] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Sliding Window Attention is enabled but not implemented for `sdpa`; unexpected results may be encountered.
Loading checkpoint shards:   0%|                                                                                   | 0/14 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained
    return model_class.from_pretrained(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 279, in _wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 4399, in from_pretrained
    ) = cls._load_pretrained_model(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 4822, in _load_pretrained_model
    state_dict = load_state_dict(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 513, in load_state_dict
    with safe_open(checkpoint_file, framework="pt") as f:
FileNotFoundError: No such file or directory: "/mnt/data/liang.zeng/models/SWE-agent-LM-32B/ft-model-00001-of-00014.safetensors"
>>> 

Unfortunately, it still doesn’t load correctly.

SWE-bench org

Oh wait i think it seems like it's looking for

FileNotFoundError: No such file or directory: "/mnt/data/liang.zeng/models/SWE-agent-LM-32B/ft-model-00001-of-00014.safetensors"

But the *.safetensors I uploaded are all prefixed with "model-", not "ft-".

Could you try either renaming your files locally or updating your serving framework to point to "model-000...safetensors" instead? Perhaps the first option is easier.

I can also update the file names to have the "ft-" prefix, not sure what the usual convention is.

Sign up or log in to comment