bytedance / bytedance/Q-Insight
加载报错 safetensors_rust.SafetensorError: Error while deserializing header: header too large
- Dominant language
- Python
- Stars
- 322
- Forks
- 13
- PR merge metrics
- No merged PRs in 30d
Description
Q-insight运行
cd src/eval/
python demo_score.py
报错
Loading checkpoint shards: 0%| | 0/4 [00:00
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
File "/root/miniconda3/envs/qinsight/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper
return func(*args, **kwargs)
File "/root/miniconda3/envs/qinsight/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4399, in from_pretrained
) = cls._load_pretrained_model(
File "/root/miniconda3/envs/qinsight/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4822, in _load_pretrained_model
state_dict = load_state_dict(
File "/root/miniconda3/envs/qinsight/lib/python3.10/site-packages/transformers/modeling_utils.py", line 513, in load_state_dict
with safe_open(checkpoint_file, framework="pt") as f:
safetensors_rust.SafetensorError: Error while deserializing header: header too large
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.