ValueError: The checkpoint you are trying to load has model type `smolvlm` but Transformers does not recognize this architecture.
@shaileshsarda
make sure to install the latest transformers:
!pip install git+https://github.com/huggingface/[email protected]
thank you!
Thank You!
torch=2.4.0+cu118，flash_attn-2.6.2+cu118torch2.4cxx11abiTRUE-cp312-cp312-linux_x86_64.whl+python3.12
git clone https://github.com/huggingface/transformers.git
cd transformers
git checkout v4.49.0-SmolVLM-2
pip install -e .
I have this problem too, have you solved it?
!pip install git+https://github.com/huggingface/[email protected]
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch
model_path = "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
processor = AutoProcessor.from_pretrained(model_path)
model = AutoModelForImageTextToText.from_pretrained(
model_path,
torch_dtype=torch.bfloat16,
_attn_implementation="flash_attention_2"
).to("cuda")
ImportError Traceback (most recent call last)
/tmp/ipython-input-28-2175807590.py in <cell line: 0>()
----> 1 from transformers import AutoProcessor, AutoModelForImageTextToText
2 import torch
3
4 model_path = "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
5 processor = AutoProcessor.from_pretrained(model_path)
ImportError: cannot import name 'AutoProcessor' from 'transformers' (unknown location)
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.
To view examples of installing some common dependencies, click the
"Open Examples" button below.