Yxxxb/VoCo-LLaMA

Issues

• number of token to store visual information

  #17 opened 7 days ago
  1

• Checkpoints

  #16 opened 9 days ago
  1

• About training

  #15 opened 2 months ago
  0

• Could you please provide the code for ablation study with LLaMA-VID

  #14 opened 9 days ago
  1

• implementation of voco token

  #13 opened 3 months ago
  1

• Find core files

  #12 opened 3 months ago
  1

• Weird loss curve

  #11 opened 4 months ago
  2

• Evaluation on Video-MME & Temporal Understanding benchmarks

  #10 opened 5 months ago
  1

• Flash attention and attention mask modification. Does the model support flash attention?

  #9 opened 5 months ago
  1

• How to compare the inference time?

  #8 opened 5 months ago
  4

• checkpoint and more benchmark results

  #7 opened 5 months ago
  1

• VoCo-LLaMA checkpoints

  #6 opened 5 months ago
  1

• Hyperparameters for different number of voco tokens

  #5 opened 5 months ago
  2

• Training Objective

  #4 opened 5 months ago
  1

• Missing setup.py or pyproject.toml

  #3 opened 5 months ago
  2

• Final Weights

  #2 opened 5 months ago
  2

• Congrats

  #1 opened 5 months ago
  1