RenShuhuai-Andy/TimeChat

Issues

• Weight for QA benchmarks

  #36 opened 21 days ago by NIneeeeeem
  2

• Asking for the Fine-tuned Checkpoint

  #35 opened 22 days ago by minjoong507
  1

• Could you test TimeChat on the EgoShema dataset?

  #34 opened a month ago by EricLina
  1

• Can this model do qa tasks？

  #26 opened 2 months ago by leexinhao
  2

• Why the result of temporal video grounding is always the multiple of 5?

  #33 opened 23 days ago by zhengrongz
  5

• Question about the output of the time-aware frame encoder

  #28 opened 23 days ago by Mingxiao-Li
  2

• Questions about the provided fine-tuning model parameters

  #30 opened 23 days ago by LanXingXuan
  1

• 用自己的数据集finetune，如何在train的过程中进行eval？

  #32 opened a month ago by changqinyao
  0

• Based transformers version needed for modifying models/modeling_llama.py

  #31 opened a month ago by yeahjack
  3

• Question about fune-tune

  #25 opened a month ago by zhengxingmao
  7

• Inference with audio

  #29 opened 2 months ago by lakshya-frontera
  2

• Question about prompt

  #20 opened 2 months ago by Ironieser
  5

• What is the relationship between segment and timetoken？

  #17 opened 3 months ago by sunwhw
  3

• When conducting SFT experiments, setting batch_size_train to 1 or 2 has the same memory usage.

  #27 opened 2 months ago by tiesanguaixia
  0

• For different video datasets, is the frame density always drawn at intervals of 1 second?

  #2 opened 5 months ago by DuoLong
  5

• the performance is very low on my own dataset.

  #22 opened 2 months ago by onlyonewater
  5

• Subset of YT-Temporal

  #24 opened 2 months ago by patrick-tssn
  1

• Question about batch size

  #23 opened 2 months ago by gyxxyg
  1

• Question about the tokenizer

  #19 opened 2 months ago by gyxxyg
  5

• Experiment-related question

  #21 opened 3 months ago by zhaodongliang678
  3

• RAM and VRAM requirement

  #13 opened 3 months ago by Coronal-Halo
  2

• Question about prompts.

  #18 opened 3 months ago by gyxxyg
  2

• Inquiry on training cost

  #16 opened 3 months ago by HenryHZY
  2

• Demo can‘t show the same desult

  #15 opened 3 months ago by xiaoxiaoli666
  1

• Bad performance of Charades

  #14 opened 3 months ago by soyeonhong
  1

• Do we need to crop the HiREST videos?

  #10 opened 4 months ago by yeliudev
  14

• Seeking Clarification about Fine-tuning Datasets

  #12 opened 4 months ago by ShramanPramanick
  2

• Details of sliding qformer operation

  #11 opened 4 months ago by jihwanp
  1

• the generalization performance is bad when testing on custom videos.

  #8 opened 4 months ago by dragen1860
  1

• torch.load raise TypeError: 'strict' is an invalid keyword argument for Unpickler()

  #9 opened 5 months ago by wwq66
  4

• Error in loading Video-LLaMA-2-7b_Finetuned

  #7 opened 5 months ago by dragen1860
  1

• When will the checkpoint and demo scripts be released?

  #5 opened 5 months ago by Hugh0120
  2

• how to evaluation on activitynet-DVC?

  #6 opened 5 months ago by TXH-mercury
  3

• UnsatisfiableError

  #4 opened 5 months ago by LarryLeeee
  4

• Checkpoints to run demo and dataset

  #3 opened 5 months ago by fazlicodes
  1

• A very good video-related work, it is convenient to open source the data set？

  #1 opened 5 months ago by Xujianzhong
  1