DAMO-NLP-SG/Video-LLaMA

Issues

• How To: Use hugging face checkpoints downloaded on a CentOS machine

  #148 opened 9 months ago by joysl
  5

• 配置文件位置在本地但是还是提示OSError: Can't load tokenizer for 'bert-base-uncased'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'bert-base-uncased' is the correct path to a directory containing all relevant files for a BertTokenizer tokenizer.

  #172 opened 3 months ago by Asmallsoldier
  0

• Hugging Face demo runtime error

  #143 opened 10 months ago by sihoseanhan
  2

• modelling_llama.py

  #166 opened 6 months ago by zeroQiaoba
  1

• Do you have plan to release Video-LLaMA checkpoints with LLaMA 3.1?

  #171 opened 4 months ago by ShramanPramanick
  1

• Issue in api endpoints

  #170 opened 5 months ago by RAJA102002
  0

• 模型错误输出结果

  #169 opened 5 months ago by shiyeeee
  0

• Evaluation on large-scale dataset

  #151 opened 9 months ago by hritam-98
  1

• Audio input

  #168 opened 6 months ago by CHEN-H01
  0

• 训练时长？

  #167 opened 6 months ago by riariam
  0

• Problem running demo: Loading checkpoint shards never finishes

  #165 opened 7 months ago by jpssoares
  1

• llm在两个阶段都是keep frozen吗？

  #160 opened 7 months ago by Nastu-Ho
  1

• Error loading the audio

  #163 opened 7 months ago by xjr01
  0

• Finetune with LoRA and QLoRA

  #162 opened 7 months ago by thisurawz1
  0

• finetune-billa7b-zh inference error shape '[-1, 136]' is invalid for input of size 137

  #161 opened 7 months ago by len2618187
  0

• What if no frame_position_embeddings?

  #158 opened 8 months ago by LetsGoFir
  0

• Unable to launch demo

  #149 opened 9 months ago by joysl
  2

• how to increase the numbers of input frame?

  #155 opened 8 months ago by onlyonewater
  2

• What is the input sample of the forward function in videollama

  #146 opened 10 months ago by llx-08
  1

• .

  #153 opened 9 months ago by advenTure423
  0

• Possible bugs in LR scheduler

  #154 opened 8 months ago by SAGNIKMJR
  0

• Compatibility b/w torch and torchvision?

  #152 opened 9 months ago by shreyakannan1205
  0

• Is video-LLaMA capable of comprehending videos that have faces surrounded by bounding boxes(face recognition)

  #150 opened 9 months ago by PhilipAmadasun
  0

• Multiple Video-Text pair Support

  #129 opened a year ago by mustafaadogan
  1

• Frame-aware?

  #142 opened 10 months ago by jayavanth
  1

• 如何提升下游任务上finetune的效果

  #147 opened 10 months ago by Jinjikiko
  0

• How to select the video encoder of the chinese version with BiLLA or Ziya ?

  #144 opened 10 months ago by cm-xcju
  2

• A demo without gradio

  #140 opened a year ago by liboliba
  1

• Incorrect model inference (what went wrong in my setup)

  #145 opened 10 months ago by jennyziyi-xu
  0

• multi-cards training

  #141 opened a year ago by gqsmmz
  0

• 关于environment.yml文件的问题

  #120 opened a year ago by balabanahei
  2

• example model deployment

  #139 opened a year ago by nahidalam
  0

• Unable to access LLaMA weights to build Vicuna-7B

  #137 opened a year ago by muzairkhattak
  1

• inf value occurs during forwarding process when fine-tuning VL branch with LLAVA-150K+MiniGPT4-3.5K+webvid-instruct

  #138 opened a year ago by xuboshen
  1

• Dear author, How much time does it cost to train this model？ With what type of GPU cards?

  #136 opened a year ago by zhangyuereal
  0

• RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM: size mismatch for model.embed_tokens.weight: copying a param with shape torch.Size([32001, 4096]) from checkpoint, the shape in current model is torch.Size([32000, 4096]). size mismatch for lm_head.weight: copying a param with shape torch.Size([32001, 4096]) from checkpoint, the shape in current model is torch.Size([32000, 4096]).

  #135 opened a year ago by Amber0913
  0

• Very poor audio understanding

  #134 opened a year ago by DumplingLife
  1

• How to finetune video-llama using deepspeed?

  #133 opened a year ago by tangyipeng100
  0

• Prompt

  #132 opened a year ago by tobyperrett
  0

• Hugging Face Spaces not working!

  #131 opened a year ago by simmimak
  1

• The question about llama parameters during pre-training and fine-tuning.

  #130 opened a year ago by cooper12121
  2

• change the frames and query_tokens size

  #128 opened a year ago by AllenFind
  0

• Interesting prompt template

  #126 opened a year ago by tian1327
  1

• Gradio does not work, stuck on uploading forever.

  #127 opened a year ago by whoishoa
  1

• Do you have any plans to open-source the pre-training and fine-tuning checkpoints based on Llama 2 Chinese version?

  #125 opened a year ago by bjcodereview3
  0

• 训练获取Dataloader中 的数据出错

  #124 opened a year ago by Junphy-Jan
  0

• how to run using LLaMA-2-chat?

  #119 opened a year ago by tarunmis
  1

• 能否更新下README

  #122 opened a year ago by Junphy-Jan
  1

• 如何部署LLama2训练出的video llama？

  #121 opened a year ago by DimplesL
  0

• 请问训练设置val，这样正确吗

  #118 opened a year ago by zhaozhipeng1997
  0