Error when using model
I am trying to extract features from my videos using the code below:
model = AutoModel.from_pretrained(
MODEL_NAME,
trust_remote_code=True,
token=HF_TOKEN # Only needed if model is gated
).eval().to(device)
But I am getting this error:
ValueError: Unrecognized model in OpenGVLab/InternVideo2-Stage2_1B-224p-f4. Should have a model_type key in its config.json, or contain one of the following strings in its name: afmoe, aimv2, aimv2_vision_model, albert, align, altclip, apertus, arcee, aria, aria_text, audio-spectrogram-transformer...
I am having trouble installing flash atn
You could try to build it in the docker container or make a new clean venv and install all dependency again
I'm too facing the same issue, flash attn installation problem ! Can someone help me with it , i even tried to bypass flash attn as it is optional but facing continuos errors !
could you try to use pip install flash-attn --no-build-isolation to bypass environment conflicts. Ensure your CUDA version, PyTorch version, and Python version (ideally 3.10 or 3.11) are mutually compatible.
Unfortunately, there is no sequence.