GAIR-NLP/anole

Issues

• Details missing in the paper

  #46 opened a month ago by Masaaki-75
  0

• Anole-HF cannot be converted to Anole-Torch accurately

  #45 opened a month ago by Hritikbansal
  0

• is this still being worked on?

  #28 opened 4 months ago by CoffeeShifter
  4

• how to disable bf16 during inference?

  #44 opened a month ago by nicolaus-huang
  0

• Inference Problem

  #42 opened 3 months ago by LKAMING97
  12

• Inference Problem

  #43 opened 2 months ago by URRealHero
  1

• Multimodal-in and multimodal-out

  #18 opened 5 months ago by JoyBoy-Su
  5

• Open-sourcing the training data

  #41 opened 3 months ago by findalexli
  0

• Question about the training data

  #37 opened 4 months ago by Epiphqny
  1

• Inference

  #40 opened 3 months ago by jungao1106
  2

• The effect is very poor after training

  #31 opened 4 months ago by coder4nlp
  5

• Help with the transformers version

  #39 opened 3 months ago by Raman1121
  0

• Question about Multimodal Input

  #38 opened 3 months ago by ZixianGao
  1

• Might I know when it will update the code of instruction finetune?

  #35 opened 4 months ago by physicsru
  1

• Can Chinese caption data be used for finetune?

  #36 opened 4 months ago by coder4nlp
  0

• Should update Transformers version

  #33 opened 4 months ago by xinlong-yang
  0

• Is it possible to load the weights across multi GPUs ?

  #7 opened 5 months ago by captainst
  4

• questions about the image generation?

  #9 opened 5 months ago by mutonix
  12

• where is vqgan decoder coming from

  #32 opened 4 months ago by Yuheng-Li
  1

• Support Hugging Face native support

  #14 opened 5 months ago by JoyBoy-Su
  1

• nan error running your example

  #23 opened 4 months ago by MeNicefellow
  4

• Some question(maybe bugs) about training

  #29 opened 4 months ago by Mr-Loevan
  0

• Inf Loss Problem When Training

  #30 opened 4 months ago by nreHieW
  1

• Causal mask in attention for text and image data

  #27 opened 4 months ago by TheTinyTeddy
  1

• Quantized Model

  #17 opened 5 months ago by JoyBoy-Su
  5

• question about the image understanding

  #25 opened 4 months ago by df2046df
  6

• Is there a plan to fix thread-safe problem in inferring?

  #26 opened 4 months ago by YiFang99
  3

• How's the image understanding performance?

  #24 opened 4 months ago by MonolithFoundation
  1

• AttributeError: 'ChameleonInferenceModel' object has no attribute 'dctx'

  #22 opened 4 months ago by vaisax
  2

• Improve model performance

  #15 opened 5 months ago by JoyBoy-Su
  1

• how much vram do i need for fine tuning or inference?

  #11 opened 5 months ago by Manni1000
  4

• How to prepare training data?

  #20 opened 5 months ago by hxdtest
  0

• can you please add the option to runn it on a cpu?

  #13 opened 5 months ago by Manni1000
  4

• Evaluation

  #19 opened 5 months ago by JoyBoy-Su
  0

• Initialize and pre-train a smaller model

  #10 opened 5 months ago by win10ogod
  2

• Anole-30B

  #16 opened 5 months ago by JoyBoy-Su
  0

• Fine-tune Anole & Chameleon (To be finished)

  #1 opened 5 months ago by sterzhang
  1

• Transformers changes

  #12 opened 5 months ago by winglian
  2

• questions on the released model and training

  #8 opened 5 months ago by ilovecv
  3

• paper？

  #2 opened 5 months ago by JoshonSmith
  2

• folder chameleon does not contain anything to install

  #4 opened 5 months ago by captainst
  2

• can the anole generate images with other resolution beyond 512x512？

  #6 opened 5 months ago by Jake-wei
  1

• bad results!

  #5 opened 5 months ago by yyyouy
  3

• the difference between training and facilitating_image_generation

  #3 opened 5 months ago by vd001
  2