Q-Future/Q-Align

Issues

• dataset for AIGCQA-30K-Image

  #25 opened a month ago by cyy-1234
  0

• Questions about modeling_llama2

  #24 opened a month ago by lbc12345
  0

• Confused about dataset split.

  #23 opened 2 months ago by ZachL1
  4

• Batch inference does not yield consistent results

  #22 opened 2 months ago by theicfire
  2

• prediction score

  #11 opened 4 months ago by Nastu-Ho
  2

• _prepare_4d_causal_attention_mask_for_sdpa does not exist

  #20 opened 2 months ago by theicfire
  3

• about the encode and decode

  #15 opened 2 months ago by learn01one
  1

• About Training with LoRA

  #18 opened 2 months ago by Gary-bk
  1

• ddp is too slow

  #19 opened 2 months ago by lliee1
  1

• how to prepare dataset for fine-tuning

  #21 opened 2 months ago by rokopi-byte
  1

• about the GPU usage

  #16 opened 3 months ago by Gary-bk
  2

• Program hangs when training from the start

  #7 opened 3 months ago by Teddy-Xiong
  8

• output decoding

  #14 opened 3 months ago by Nastu-Ho
  1

• How to train without huggingface_hub and offline?

  #13 opened 3 months ago by RollingWang
  1

• AttributeError when doing inference

  #12 opened 4 months ago by machengcheng2016
  1

• aesthetic assessment is sensitive to the size of the input image

  #10 opened 4 months ago by Nastu-Ho
  1

• NameError: name 'Cache' is not defined

  #9 opened 4 months ago by rokopi-byte
  1

• install error

  #6 opened 4 months ago by Hanbo-Sun
  1

• Scoring each video frame using Q-Align

  #8 opened 4 months ago by Nastu-Ho
  1

• bug encountered when running HF AutoModelForCausalLM

  #3 opened 5 months ago by asrlhhh
  2

• Missing positional argument: 'layer_idx' when using QAlignVideoScorer

  #4 opened 5 months ago by johind
  2

• About the precision of the conversion of ava dataset

  #1 opened 5 months ago by Qiulin-W
  1