magic-research/PLLaVA

Issues

• TypeError: PllavaProcessor.__init__() got an unexpected keyword argument 'image_token'

  #87 opened a month ago by bozagina
  1

• TGIF-QA evaluation crashing

  #82 opened 4 months ago by geomlyd
  3

• why the output is blank

  #81 opened 4 months ago by BOYJZ
  4

• Training loss curve

  #66 opened 2 months ago by hukkai
  2

• The inference result is all like a mess

  #63 opened 7 months ago by lucasjinreal
  3

• The download link has expired

  #86 opened 2 months ago by m1nt07
  0

• Is the inference done using only one <image> token?

  #75 opened 6 months ago by gowreesh-mago
  3

• High video loss

  #70 opened 6 months ago by TonyXuQAQ
  1

• how to train train_tcllava_7b.sh on multi machines?

  #85 opened 3 months ago by Wiselnn570
  0

• flash-attn

  #84 opened 3 months ago by AAwilliam
  0

• Why is the answer to this demo blank

  #80 opened 4 months ago by DoigtByou
  2

• Does PLLAVA possess the capability to follow instructions?

  #83 opened 4 months ago by Pride-Huang
  0

• Eval Results.

  #73 opened 6 months ago by liguopeng0923
  6

• environment failed

  #79 opened 5 months ago by chenxinhua
  0

• Hi, how does the <image> being replaced in PLLava

  #60 opened 7 months ago by lucasjinreal
  1

• Image token process malfunction

  #78 opened 5 months ago by Stevetich
  0

• Multi-GPU Inference for 34B Model

  #48 opened 7 months ago by serwansj
  1

• What's the 7B model score on mvbench?

  #53 opened 7 months ago by MonolithFoundation
  1

• The Avg. results in the PLLaVA paper is wrong!

  #55 opened 7 months ago by huangshiyu13
  2

• How to prepare eval dataset.

  #57 opened 7 months ago by linxid
  4

• About the lora config alpha and rank

  #58 opened 7 months ago by lucasjinreal
  2

• No module named dataset

  #76 opened 6 months ago by liguopeng0923
  1

• Which train_corpus was used by train pllava-13b?

  #69 opened 6 months ago by gaowei724
  0

• Question about the training data

  #74 opened 6 months ago by Kendrick-Powehi-Z
  0

• Training dataset keys_indexfile

  #72 opened 6 months ago by linxid
  0

• Training Dataset

  #71 opened 6 months ago by linxid
  1

• Difference of videochat2 jsons and magic jsons.

  #52 opened 7 months ago by OliverHxh
  2

• Instruction follow ability is weak

  #68 opened 6 months ago by lmx760581375
  7

• [TRAINING DATA]About the number of video_qa in magic_jsons, which is more than the reported number in PLLaVA paper!

  #67 opened 6 months ago by YeeShih
  0

• How can we quantize the 34B model for inference?

  #46 opened 7 months ago by ApoorvFrontera
  3

• Clarifying Ambiguity in Training Data

  #47 opened 7 months ago by patrick-tssn
  3

• The load_video function does not seem right in eval_utils.py

  #65 opened 7 months ago by ahmadmobeen
  0

• What is the prompt used to evaluate models answer on VideoChatGPT generation benchmark?

  #64 opened 7 months ago by ADiko1997
  0

• Inference error

  #61 opened 7 months ago by lucasjinreal
  4

• How to fintune base on your fintuned result

  #56 opened 7 months ago by liuao743
  2

• Abou the dataset

  #59 opened 7 months ago by lucasjinreal
  0

• Training time consumption

  #51 opened 7 months ago by hmxiong
  2

• eval on fintuning model

  #50 opened 7 months ago by liuao743
  8

• How to train only the projector?

  #54 opened 7 months ago by gaowei724
  2

• finetune problem

  #43 opened 7 months ago by AshOneN
  3

• No output text when evaluating on my own pre-trained model.

  #45 opened 7 months ago by gaowei724
  5

• Checkpoints for trained models?

  #49 opened 7 months ago by serwansj
  1

• It seems that the most effective point of increase is to increase the size of llm

  #44 opened 7 months ago by xmy0916
  0

• Possible error in doctring for "pixel_values"

  #42 opened 7 months ago by tomyoung903
  0

• Can PLLaVA caption rectangular videos without cropping?

  #38 opened 8 months ago by tomyoung903
  1

• Finetune my own's tasks based on pllava-7b, but got "image_to_overwrite.sum() != image_features.shape[:-1].numel()" assertion failure.

  #39 opened 7 months ago by gaowei724
  1

• Bug in tasks/eval/eval_utils.py

  #40 opened 8 months ago by patrick-tssn
  1

• Dataset Resquest

  #36 opened 8 months ago by mingzeG
  2

• CLI inference

  #37 opened 8 months ago by YepJin
  0

• About vram and int-4 version

  #35 opened 8 months ago by joseph16388
  0