Nimesh Agrawal
Nimesh Agrawal
Any solution found regarding this issue?
The problem is there in the datasets/purchase/datasetfile. They have hard coded train and test sample size. The prepare_data.py splits according to test_size = 0.2, but "datasetfile" has sample sizes according...
Hi @Lee-xeo , have you resolved the issue? Even using the -HF suffix doesn't help.
@Weiyun1025 Can you provide the solution
@Lee-xeo Thanks for sharing. But is there a way to make it work with -HF version too? Because as per documentation in this: https://huggingface.co/docs/transformers/v4.55.4/en/model_doc/internvl#video-input, it does not work.
@nguyen-khang-ntq There is another alternative to fix this bug. While processing the messages, we can use the following: inputs = processor.apply_chat_template( messages, return_tensors="pt", add_generation_prompt=True, tokenize=True, return_dict=True, fps=fps, size={"height": height, "width":...