huangb23/VTimeLLM

Issues

• About training.

  #34 opened 4 months ago by EdenGabriel
  0

• RuntimeError: The size of tensor a (147) must match the size of tensor b (293) at non-singleton dimension 3

  #33 opened 4 months ago by Vijaysivadas
  0

• Code to generate Stage 3 dataset from ActivityNet or DiDeMo

  #32 opened 4 months ago by anilbatra2185
  0

• stage2 features

  #31 opened 5 months ago by simplewhite9
  2

• How much time does it take to extract features in stage 2 and what is the hardware used?

  #25 opened 5 months ago by Maulog
  4

• Feature extraction code requirement

  #30 opened 5 months ago by L4zyy
  1

• About Activitynet eval process

  #29 opened 5 months ago by lixuefenfen
  3

• About evaluation

  #28 opened 5 months ago by EdenGabriel
  0

• Id corrspondence

  #27 opened 6 months ago by wayne3771
  2

• Low accuracy rate

  #26 opened 6 months ago by wayne3771
  5

• Why did you use the only subset?

  #23 opened 6 months ago by MSungK
  1

• NVIDIA Driver error - could not parse ModelProto

  #24 opened 6 months ago by simran0112
  2

• Linking id to DiDeMo video path

  #21 opened 6 months ago by ZhangYuanhan-AI
  3

• Training Warning

  #20 opened 7 months ago by Tanveer81
  1

• Missing intern_clip_feat

  #22 opened 7 months ago by Tanveer81
  0

• About lora duplication

  #19 opened 7 months ago by yeppp27
  6

• can I simply query the model to locate the `highlight moment or the best moment` in the video?

  #17 opened 7 months ago by dragen1860
  2

• You are using a model of type llama to instantiate a model of type VTimeLLM. This is not supported for all configurations of models and can yield errors. ?

  #18 opened 7 months ago by dragen1860
  1

• Moment Localization Evaluation

  #16 opened 7 months ago by Tanveer81
  0

• Are you working on exposing an inference endpoint on huggingface or replicate?

  #15 opened 9 months ago by nwaughachukwuma
  1

• Will the test data and code in the paper be released?

  #9 opened 9 months ago by hlz0606
  1

• Running VTimeLLM inference Offline

  #14 opened 9 months ago by dengandong
  0

• chatglm3的中文理解能力怎么样？

  #12 opened 9 months ago by lucasjinreal
  3

• Main differences between VTimeLLM and LLaVA

  #13 opened 9 months ago by itruonghai
  1

• Tokenization mismatch

  #10 opened 10 months ago by weiyuan-c
  6

• 13B model ？

  #8 opened 10 months ago by vhzy
  1

• RuntimeError: cu_seqlens_q must have shape (batch_size + 1)

  #11 opened 10 months ago by KlayMa527
  1

• InternVID training dataset

  #4 opened 10 months ago by LengSicong
  2

• question about missing features?

  #3 opened 10 months ago by vhzy
  1

• when training available?

  #1 opened a year ago by vhzy
  2