dvlab-research LLaMA-VID issues

dvlab-research / LLaMA-VID

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

Apache License 2.0

742 stars 44 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Typo in scripts/extra_tool/extract_movienet_features.py

#110 HaydenMM opened 3 weeks ago
0
How to turn off parallel training

#109 tang1234567777 opened 1 month ago
0
An error was encountered when executing the cli.py

#108 Gechenseu opened 1 month ago
0
Subtitile appended

#107 ssantos97 opened 1 month ago
0
A question about the image token.

#106 Syloveslife opened 1 month ago
0
image sft data

#105 Yxxxb opened 2 months ago
0
在线演示的DEMO打不开了

#104 JingyuLi-code opened 2 months ago
0
coco

#103 ppingzhang closed 2 months ago
0
OpenAI API

#102 YingYellow opened 2 months ago
0
Cannot reproduce VideoChatGPT generative performance results

#101 xsgldhy opened 3 months ago
2
Long Video Inference Evaluation Question

#100 pencilkobayashi opened 4 months ago
0
Please switch to 'llama-vid-vicuna-7b-short' to chat with upload short videos. After switch, you can clear the conversaton then retry.

#99 SCUTE-ZZ opened 4 months ago
0
Gradio Web IU doesn't work

#98 irisgong1020 opened 4 months ago
0
Why using first 39 blocks of the total 40 blocks in eva-vit-g?

#97 wangkunyu241 opened 4 months ago
0
unable to get results when evaluating on msvd-qa benchmark

#96 irisgong1020 closed 4 months ago
0
AssertionError: Size mismatch! image_features: 1, prompts: 8

#95 szbcasia opened 6 months ago
0
I was reasoning on the GPU L20(48GB) machine and still burst the video memory

#94 try2020-code opened 6 months ago
0
OOM in stage2 finetuning

#93 Nastu-Ho opened 6 months ago
1
_StoreAction.__init__() got an unexpected keyword argument 'defalut'

#92 try2020-code opened 6 months ago
1
2 tokens in inference

#91 XinyuJiang closed 6 months ago
1
About mm_projector loading issue

#90 rubylan opened 6 months ago
1
[h264 @ 0x871b380] mmco: unref short failure during stage-2 training

#89 Nastu-Ho opened 6 months ago
0
training loss in stage-1

#88 Nastu-Ho opened 6 months ago
1
code details

#87 Nastu-Ho closed 7 months ago
0
Extract context relevancy

#86 IgnacioSan22 opened 7 months ago
0
KeyError: 'LlavaConfig'

#85 skyol99 opened 7 months ago
1
How to resume the checkpoint to continue pretraining？

#84 Einstone-rose opened 7 months ago
0
About the WebVid dataset

#83 szbcasia opened 7 months ago
1
Are all video-based checkpoints trained with 2 tokens?

#82 haodi19 opened 7 months ago
0
HF model format : vlm weights not in llama-vid-7b-full-336

#81 nileshkokane01 opened 7 months ago
0
Questions about Text Decoder and Text Query

#80 xiaokj37 opened 7 months ago
0
About the json in stage2 and stage3

#79 liziming5353 opened 7 months ago
1
about the context length for long video

#78 zhuqiangLu opened 7 months ago
0
Confusion in pre-process images for long video

#77 zhuqiangLu closed 7 months ago
0
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1! (when checking argument for argument weight in method wrapper_CUDA__native_layer_norm)

#76 daocodedao opened 8 months ago
2
About ZERO3

#75 xxtars closed 8 months ago
7
An error occurs during the stage 2 fine-tuning

#74 ShuoZhang2003 opened 8 months ago
1
AttributeError: 'NoneType' object has no attribute 'is_loaded'

#73 sykuann opened 8 months ago
1
why not use LoRA for tunning Vicuna?

#72 dragen1860 closed 7 months ago
1
Multi-image inference

#71 g-h-chen opened 8 months ago
1
Computation costs for each stage?

#70 Becomebright closed 8 months ago
1
Requirements needed for inferring llama-vid llama-vid-13b-full-224-video-fps-1

#69 sykuann opened 8 months ago
1
abnormal outputs for llama-vid-7b-full-224-video-fps-1 ckpt

#68 YulongBonjour opened 8 months ago
1
How to change default path for model_zoo

#67 sykuann opened 8 months ago
2
Questions about the subtitles.

#66 Yxxxb opened 9 months ago
1
flash-attn

#65 ismailukman closed 9 months ago
2
error: llava key

#64 menahem-borges-rodrigues closed 9 months ago
1
About evaluation on vqav2 dataset

#63 liziming5353 opened 9 months ago
1
Long video dataset (only available 167 movies)

#62 KerolosAtef closed 8 months ago
2
Long Video dataset

#61 eslambakr opened 9 months ago
1