PKU-YuanGroup/Video-LLaVA

Issues

• Video-LLaVa now available in the Transformers library!

  #156 opened 7 months ago by zucchini-nlp
  56

• Help with evaluation script for lora finetuned model.

  #195 opened 2 months ago by marvlyngkhoi
  0

• missing file: preprocessor_config.json

  #186 opened 5 months ago by JunanPan
  1

• Multi-GPU inference problem.

  #179 opened 5 months ago by jiazheng-xing
  1

• Hardware Requirement for the model to run in LORA

  #194 opened 2 months ago by leochang123
  0

• Videochatgpt tuning data encounters some error

  #193 opened 2 months ago by Lexarymade
  1

• Can you Fix the DEMO. Demo is no longer working

  #192 opened 2 months ago by thisurawz1
  0

• Pretrain and Finetune template versions

  #189 opened 4 months ago by xin-li-67
  1

• ImportError: cannot import name '_expand_mask' from 'transformers.models.clip.modeling_clip'

  #184 opened 5 months ago by qiuchen001
  4

• Unable to install flash attn module

  #143 opened 8 months ago by anantalp
  1

• Can't reproduce results on MSRVTT and MSVD dataset

  #191 opened 3 months ago by 1999Lyd
  0

• Size mismatch error when running locally.

  #152 opened 7 months ago by ssuncheol
  3

• Issues with Converting the video-llava Model to ONNX

  #190 opened 4 months ago by Ark1a
  0

• 训练时报错AttributeError: 'DeepSpeedCPUAdam' object has no attribute 'ds_opt_adam'

  #144 opened 8 months ago by Qinger27
  5

• When I evaluated the ‘TGIF_Zero_Shot_QA’ dataset, the accuracy was only 13%. Should I train first to achieve the 70% accuracy in the paper?

  #188 opened 4 months ago by FanshuoZeng
  0

• May I ask what is the api_base used for evaluation?

  #187 opened 4 months ago by FanshuoZeng
  0

• Can this model apply a few-shot when inference?

  #185 opened 5 months ago by Ijustakid
  0

• Valley video not found during pretraining.

  #182 opened 5 months ago by Aakriti05
  0

• Api is not running properly getting errors In each endpoint

  #181 opened 5 months ago by RAJA102002
  0

• Questions about LanguageBind Usage

  #180 opened 5 months ago by lingjunzhao
  0

• Issues with finetune_lora.sh

  #171 opened 6 months ago by shag1802
  2

• Request for Inference Parameters on VideoLLava

  #178 opened 5 months ago by adrianwestmoon
  0

• Is it possible to train with languages other than English, and are the 8 frames sampled uniformly across different video lengths?

  #177 opened 5 months ago by YoungjaeDev
  0

• error:RuntimeError: Error(s) in loading state_dict for CLIPVisionModel: size mismatch for vision_model.embeddings.class_embedding: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).

  #175 opened 6 months ago by zapqqqwe
  3

• size mismatch

  #176 opened 6 months ago by cs19469
  0

• total_frames zero error

  #174 opened 6 months ago by OliverLeeXZ
  0

• pretrained checkpoint

  #173 opened 6 months ago by OliverLeeXZ
  0

• How to increase the sample frames amount

  #172 opened 6 months ago by sherlock666
  0

• Video-LLava Upgradation

  #164 opened 7 months ago by Tortoise17
  1

• ERROR opening+moov atom not found+mmco: unref short failure

  #163 opened 7 months ago by Frank-Dg
  2

• Error with Gradio Client: Please Upgrade Gradio to 4.x and Redeploying HuggingFace Space

  #170 opened 6 months ago by zhanwenchen
  0

• Question Regarding Video Frame Processing

  #169 opened 6 months ago by Kkkaystone
  0

• How to install videollava together with xformer?

  #168 opened 6 months ago by zengbohan0217
  0

• extremely slow with transformers

  #167 opened 6 months ago by RaulKite
  0

• Training help

  #166 opened 7 months ago by felmoreno1726
  0

• About class embedding

  #165 opened 7 months ago by feiyu12138
  0

• Problem about pretrain parameter dim size is differen to the model dim size?

  #151 opened 8 months ago by NEC09818
  1

• Can the confidence coefficient of an answer be obtained?

  #162 opened 7 months ago by IsabelJimenez99
  0

• Inference model path unclear

  #161 opened 7 months ago by Ali2500
  0

• Please specifiy library versions

  #159 opened 7 months ago by nahidalam
  0

• Uri validation issue on Replicate

  #157 opened 7 months ago by Gab1988
  1

• The problem about the environment

  #154 opened 7 months ago by swiftCC
  0

• Some weights of the model checkpoint at "./Video-LLaVA-7B" were not used when initializing LlavaLlamaForCausalLM:

  #153 opened 7 months ago by ssuncheol
  0

• how to load pretrained weight on local (offline)?

  #150 opened 8 months ago by jusepv
  0

• Warnings about weights, temperature, top_p, and embedding layer, but it still works. Should I worry about them?

  #149 opened 8 months ago by secretlycarl
  0

• Impossible to install on windows

  #148 opened 8 months ago by secretlycarl
  0

• 推理多张图片时报错 IndexError: list index out of range

  #146 opened 8 months ago by Qinger27
  1

• Seems it has very limited understanding ability..

  #142 opened 8 months ago by advenTure423
  0

• 为什么loss一直为0

  #141 opened 8 months ago by xienan0326
  0

• About contrastive learning

  #140 opened 9 months ago by mjkmain
  0