What is the conv-mode for LLaVA-NeXT-Video-7B-32K

[llava-vl]

What is the conv-mode for LLaVA-NeXT-Video-7B-32K

[ZhangYuanhan-AI]

LLaVA-NeXT/playground/demo/video_demo.py

Line 160 in 6944062

output_ids = model.generate(inputs=input_ids, images=video, attention_mask=attention_masks, modalities="video", do_sample=True, temperature=0.2, max_new_tokens=1024, use_cache=True, stopping_criteria=[stopping_criteria])

try to change this line to

output_ids = model.generate(inputs=input_ids, images=video, attention_mask=attention_masks, modalities="video", do_sample=True, temperature=0.2, max_new_tokens=1024, use_cache=True)

[ZhangYuanhan-AI]

Hi, what is the version of your transformers?

[rebuttalpapers]

Thanks!

import transformers
print(transformers.version)

4.40.0.dev0

[ZhangYuanhan-AI]

My TF version is 4.39.0 and the conv model should be mistral_instruct for LLaVA-NeXT-Video-7B-32K.

BTW, there is "attention_dropout" in "https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-7B-32K/blob/main/config.json"

[rebuttalpapers]

Thanks @ZhangYuanhan-AI !

1. What is the "attention_dropout" and how it solves the problem above "AttributeError: 'LlavaMistralConfig' object has no attribute 'attention_bias'"?

2. Additionally, I downgraded the TF from 4.40.0.dev0 to 4.39.0 and the same problem is still there.

3. what is the command you use to call LLaVA-NeXT-Video-7B-32K model?
   (for others it is: bash scripts/video/demo/video_demo.sh lmms-lab/LLaVA-NeXT-Video-7B-DPO vicuna_v1 32 2 True ./data/llava_video/video-chatgpt/evaluation/Test_Videos/v_Lf_7RurLgp0.mp4)

4. I added the following 3 lines for config, not sure whether they are correct or not:
   setattr(cfg_pretrained, 'attention_bias', 0)
   setattr(cfg_pretrained, 'rope_scaling', {"factor": 8.0, "type": "linear"})
   setattr(cfg_pretrained, 'pretraining_tp', 1)
   However, it is not giving any response

Time taken for inference: 2.013814687728882 seconds
Question: [INST]
Please provide a detailed description of the video, focusing on the main subjects, their actions, and the background scenes [/INST]

Response: