NVlabs/VILA

Issues

• What is the conv_mode for VILA-1.5-3B ?

  #103 opened a month ago by amitbcp
  1

• Expected Release Date for VILA^2 Model and Code

  #124 opened 4 months ago by SZUHvern
  1

• ValueError: The checkpoint you are trying to load has model type `llava_llama` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

  #135 opened a month ago by eternal8080
  14

• Context size and examples for LongVILA

  #141 opened 3 months ago by yulinzou
  1

• KeyError: 'llava_llama'

  #138 opened 3 months ago by RajaAIStarter
  1

• cannot download dataset

  #139 opened a month ago by henrycjh
  1

• Unable to run Gradio demo: VILA with TinyChat

  #146 opened 2 months ago by mitraavi
  1

• How to get the stage 2 checkpoint path for 3_sft.sh

  #143 opened 2 months ago by Qnancy
  5

• What is the conv_mode for VILA1.5-40b in video inference?

  #145 opened 2 months ago by stdKonjac
  1

• Fine-tuning LongVILA

  #140 opened 3 months ago by lyluh
  2

• Repetitive Output in LongViLa-LLama3-1024Frames

  #149 opened a month ago by hb-jw
  1

• How to run longvila large context, sequence parallel inference?

  #130 opened 4 months ago by zadeismael
  20

• How to change openai inference call to docker for video?

  #148 opened a month ago by cholland-nv
  0

• Docker setup gets error

  #147 opened a month ago by cholland-nv
  1

• How to inference with AWQ in linux shell.

  #144 opened a month ago by GitMonkey0
  0

• Is the 2D Seq parallelism equivalent to the USP in LongVILA?

  #116 opened 4 months ago by hijkzzz
  1

• Dataset and Training code for Longvila

  #132 opened 4 months ago by JcWang20
  3

• TypeError: LlamaRotaryEmbedding.forward() got an unexpected keyword argument 'seq_len' when running VILA model inference

  #126 opened 4 months ago by LanceLeonhart
  4

• Long context video module only

  #142 opened 3 months ago by MH-Python
  0

• VILA-1.5-HD coming soon?

  #137 opened 3 months ago by collinmccarthy
  1

• About sharegpt_video. How do you make video file from jpeg images?

  #113 opened 4 months ago by osttkm
  2

• About the inference on video.

  #134 opened 3 months ago by trinhvg
  1

• create long-video QA samples

  #121 opened 4 months ago by peiliu0408
  3

• Issue with Flash Attention on V100 GPU for Llama-3-VILA1.5-8B Model

  #109 opened 5 months ago by vedernikovphoto
  8

• how to run VILA1.5-40B-AWQ

  #125 opened 4 months ago by chenxinhua
  1

• Trying to run VILA on triton with triton_llm backend

  #133 opened 4 months ago by dand-milestone
  0

• Where is the server.py script?

  #131 opened 4 months ago by zixinglin07
  0

• [HELP] Do we have any docker image for Jetson platform ?

  #111 opened 4 months ago by lenoardshannon
  2

• How to run vila with TinyChatEngine with multiple understanding enabled?

  #129 opened 4 months ago by yg1988
  0

• Fine tuning and --evaluation_strategy argument

  #122 opened 4 months ago by lyluh
  1

• Can VILA do grounding jobs?

  #128 opened 4 months ago by PredyDaddy
  1

• Plz fix run_vila.py line 65 output variable(s)

  #127 opened 4 months ago by ziyaosg
  0

• Data preparation for Stage 4 and Stage 5 in LONGVILA

  #119 opened 4 months ago by GenjiB
  0

• LongVILA - compatibility with other LLMs

  #115 opened 4 months ago by orrzohar
  1

• COYO-700M Dataset Download Script Error

  #107 opened 4 months ago by XuGW-Kevin
  3

• Support for multi-video captioning with multiple grid image inputs?

  #96 opened 4 months ago by YoungjaeDev
  2

• How to convert model to gguf

  #93 opened 4 months ago by dand-milestone
  3

• No training scripts in scripts/v1_5/paper/

  #112 opened 4 months ago by yhyang123
  1

• Whether the visual encoder participates in training

  #95 opened 4 months ago by LoverLost
  3

• Image text retrieval support

  #106 opened 4 months ago by lhchau
  1

• Support VILA with lmdeploy

  #105 opened 4 months ago by cmpute
  1

• [Help] Using VILA1.5-40b model for Video Descriptions

  #110 opened 5 months ago by SidPad03
  1

• Is there any way to increase the context window?

  #100 opened 5 months ago by ZackBradshaw
  4

• Deployment to SageMaker and/or HuggingFace Inference Endpoints Fails With Error

  #94 opened 5 months ago by averypfeiffer
  5

• Question re. LanguageModel vs LanguageModelForCausalLM functionalies

  #101 opened 5 months ago by orrzohar
  2

• AttributeError: 'Image' object has no attribute 'shape'

  #104 opened 5 months ago by ZackBradshaw
  6

• question: what does 'repack_multimodal_data' function do?

  #98 opened 5 months ago by orrzohar
  1

• release schedule for the "VILA1.5-34b-4bit-AWQ" model.

  #99 opened 5 months ago by xiexiaoshinick
  1

• Multi-Image or Multi-Video Inference Example

  #97 opened 5 months ago by chancharikmitra
  2

• Llama2 or Llama3

  #102 opened 5 months ago by amitbcp
  0