Upload folder using huggingface_hub

Delete ckpt/sft_llava_next_video_llama3_mix_sft_multi_modal_projector_video_projecter_language_model.pth

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Update README.md

Delete llama3-llava-next-8b-seperated/language_model_seperated/model.safetensors.index.json.1

Upload folder using huggingface_hub

Delete vision_model.pth

Delete tokenizer_config.json

Delete tokenizer.json

Delete special_tokens_map.json

Delete multi_modal_projector.pth

Delete image_newline.pth

Delete generation_config.json

Delete config.json

Delete language_model_seperated

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Delete ckpt/pretrain_llava_next_video_llama3_mix_pretrain_multi_modal_projector_video_projecter.pth

Update README.md

Delete G-VideoQA-gpt4o-mini-anno.json

Create README.md

Upload pretrain_llava_next_video_llama3_mix_pretrain_multi_modal_projector_video_projecter.pth

Delete pretrain_llava_next_video_llama3_mix_pretrain_multi_modal_projector_video_projecter.pth

Upload pretrain_llava_next_video_llama3_mix_pretrain_multi_modal_projector_video_projecter.pth

Upload G-VideoQA-gpt4o-mini-anno.json

Delete Phi-3.5-vision-instruct-seperated/language_model.pth

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit