Video-LLaMA
Video-LLaMA copied to clipboard
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Hi. What is the full text that the model sees for the demo running in huggingface? Does it include any special tags/sys messages etc.? Thanks.
Hi, I am running the demo with only VL branch, I set the checkpoint path like: ```shell llama_model: "model_weights/vicuna_final/" ckpt: '/home/ubuntu/Documents/Video-LLaMA/model_weights/Pre-trained_Visual_Encoder/pretrained_minigpt4.pth' # you can use our pretrained ckpt from https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained/...
Hi, Thanks a lot for your great work! I am wondering if we can change the sampling frames and query_tokens size.
Hi guys, Now I can fine-tune 'visionbranch_stage2_finetune.yaml' on **four** A100 80GB GPUs using gradient accumulation. I'd like to know at what point the Loss is considered to have converged? For...
Before repair: ```bash TypeError: Caught TypeError in DataLoader worker process 6. File "/video_llama/datasets/datasets/webvid_datasets.py", line 70, in __getitem__ video_path = self._get_video_path(sample_dict) File "/video_llama/datasets/datasets/webvid_datasets.py", line 50, in _get_video_path rel_video_fp = os.path.join(sample['page_dir'], str(sample['videoid'])...
8月更新了llama基础的video llama,demo似乎没有更新,请问如何部署?
在yaml文件中添加: `evaluate: False train_splits: ["train", "val"] train_dataset_ratios: {"train":0.7, "val":0.3}`
data = self._data_queue.get(timeout=timeout) 获取数据获取不到 训练一直僵死,走不下去
可以提供一个infer的脚本吗?非gradio demo的那种