PKU-YuanGroup/Video-LLaVA

Issues

• About the license

  #139 opened 9 months ago
  0

• Similarity index and time - codes

  #138 opened 9 months ago
  0

• Tendency to keep repeating the same sentence

  #137 opened 9 months ago
  2

• image / video with different MLPs

  #136 opened 9 months ago
  0

• Unable inference video locally.

  #135 opened 9 months ago
  1

• Gradio APP upgrade

  #134 opened 9 months ago
  0

• How should I obtain llava_image_tune_.json, videochatgpt_tune_.json, and nlp_tune.json

  #133 opened 9 months ago
  5

• Reproducibility. Can't install the project `pip install -e .`

  #132 opened 9 months ago
  0

• Error when loading released model on huggingface

  #131 opened 9 months ago
  0

• How should I obtain llava_image_tune_.json, videochatgpt_tune_.json, and nlp_tune.json

  #130 opened 9 months ago
  1

• ImportError: dlopen: cannot load any more object with static TLS

  #128 opened 9 months ago
  0

• finetune with lora

  #127 opened 9 months ago
  14

• We couldn't connect to 'https://huggingface.co' to load this file

  #126 opened 9 months ago
  1

• Tokenizer in different code version

  #125 opened 7 months ago
  0

• Is there any way to speed up the inference

  #124 opened 9 months ago
  4

• How to increase frame from 8 to a bigger number

  #123 opened 9 months ago
  10

• How to set the config to use multi node and multi GPUS?

  #122 opened 10 months ago
  1

• RuntimeError : Error(s) in loading state_dict for LlavaLlamaForCausalLM

  #121 opened 10 months ago
  2

• 解码器设置为opencv时，某些视频在推理时出现异常

  #120 opened 10 months ago
  0

• Transformer version

  #119 opened 10 months ago
  1

• Huggingface data files - corrupted zip files?

  #118 opened 10 months ago
  2

• 推理过程中出现错误

  #117 opened 10 months ago
  3

• Invalid link to MoE-LLaVA

  #116 opened 10 months ago
  2

• Parameter Explanations

  #115 opened 10 months ago
  2

• video eval error

  #114 opened 10 months ago
  4

• huggingface demo is broken

  #113 opened 10 months ago
  1

• Error while loading finetuned model for inferencing.

  #112 opened 10 months ago
  2

• What is the minimum gpu ram required for the video model to run?

  #111 opened 10 months ago
  1

• How to limit the generated text token to a maximum of 77?

  #110 opened 10 months ago
  1

• "RuntimeError: CUDA error: device-side assert triggered"

  #109 opened 10 months ago
  6

• Inference on more than 8 frames

  #108 opened 10 months ago
  2

• when training new model, I got stuck in the middle of the training

  #107 opened 10 months ago
  3

• Error while feeding the filter graph

  #106 opened 10 months ago
  1

• 推理 GPU bug

  #105 opened 10 months ago
  2

• 断言错误问题

  #104 opened 10 months ago
  1

• Repository- transformers config missmatch

  #103 opened 10 months ago
  3

• Distributed Inference Doesn't Work

  #102 opened 10 months ago
  10

• Can the model be used with 2 images as an input

  #101 opened 10 months ago
  1

• TypeError: 'NoneType' object is not callable

  #100 opened 10 months ago
  3

• Finetuning with LORA

  #99 opened 10 months ago
  2

• IndexError: list index out of range

  #98 opened 10 months ago
  1

• Relation of Video-LLaVA and LanguageBind

  #97 opened a year ago
  1

• Evaluation on MSVD difference from MS (0.49, 2.9 vs 0.703, 3.9)

  #96 opened a year ago
  7

• 推理bug

  #95 opened a year ago
  14

• Clarification question about model training

  #94 opened a year ago
  1

• Offline load checkpoint error

  #93 opened a year ago
  2

• Where is model saved after instruction tuning?

  #92 opened a year ago
  10

• 在online demo上传长视频时网页报错

  #91 opened a year ago
  4

• 有人遇到运行视频推理index out of bounds这个问题吗？

  #90 opened a year ago
  3

• Hi， is there a bug in Video-LLaVA-main/videollava/model/multimodal_encoder/builder.py?

  #89 opened a year ago
  8