Video-LLaMA

Video-LLaMA copied to clipboard

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.

tobyperrett

Error(s) in loading state_dict for VideoLLAMA

4

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/...

tiesanguaixia

Hi, Thanks a lot for your great work! I am wondering if we can change the sampling frames and query_tokens size.

AllenFind

After completing the fine-tuning of 'visionbranch stage2', what should be its loss value to be considered as having correctly converged?

2

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...

joeking11829

bjcodereview3

Fixed training interrupt bug

1

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'])...

bobo0810

8月更新了llama基础的video llama，demo似乎没有更新，请问如何部署？

DimplesL

在yaml文件中添加： `evaluate: False train_splits: ["train", "val"] train_dataset_ratios: {"train":0.7, "val":0.3}`

zhaozhipeng1997

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

hudielv

可以提供一个infer的脚本吗？非gradio demo的那种

3

可以提供一个infer的脚本吗？非gradio demo的那种

CaicaiJason