model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2.5-VL-3B-Instruct-AWQ", torch_dtype="auto", device_map="auto" )
#6
by
ken4005
- opened
from transformers.modeling_utils import shard_checkpoint
ImportError: cannot import name 'shard_checkpoint' from 'transformers.modeling_utils' (D:\miniconda3\envs\transPy39\lib\site-packages\transformers\modeling_utils.py)
torch 2.4.1+cu124
torchvision 0.19.0 1
tqdm 4.67.1
transformers 4.53.0.dev0
I have:
torch=2.5.1+cu121
torchvision= 0.20.1+cu121
transformers=4.52.3