facebookresearch/chameleon

Issues

• Finetuning input / target formatting

  #70 opened 2 months ago by AetherPrior
  1

• python 3.11 requirement

  #69 opened 2 months ago by matteobrina
  0

• JPEG ENCODING

  #68 opened 2 months ago by edmondja
  0

• The images generated by Chameleon are completely meaningless

  #67 opened 2 months ago by zsj555
  0

• Unable to run on V100 card

  #39 opened 6 months ago by vodp
  5

• How to generate output images

  #11 opened 6 months ago by kl2004
  4

• from transformers import ChameleonForCausalLM, ChameleonProcessor ImportError: cannot import name 'ChameleonForCausalLM' from 'transformers' (/usr/local/lib/python3.11/site-packages/transformers/__init__.py)

  #58 opened 5 months ago by Iven2132
  2

• Training code for VQ-GAN

  #65 opened 4 months ago by karrykkk
  1

• websocket won't connect (7102)

  #66 opened 4 months ago by Oracle42069
  3

• Loading Never Complete with Docker Compose

  #54 opened 5 months ago by MeNicefellow
  2

• The generated image does not make any sense.

  #60 opened 5 months ago by MaureenZOU
  2

• Does the 30B Model from hugginface support Single GPU Inference ?

  #61 opened 5 months ago by neoyxm
  1

• Single GPU bug with python -m chameleon.miniviewer

  #59 opened 5 months ago by MaureenZOU
  6

• Accessing VQGAN Checkpoint

  #51 opened 5 months ago by YiFang99
  2

• 下载个pretrained model申请也就罢了，还给我拒了，科学无国界？

  #55 opened 5 months ago by zhangbaijin
  0

• Request for the details in VQAv2 evaluation

  #52 opened 5 months ago by Leun9
  0

• Is this model going to support batch generation for multimodal?

  #56 opened 5 months ago by YiFang99
  1

• Why Answers are different for repeating the same text question + same input image

  #47 opened 5 months ago by usajid14
  2

• Hugging Face links in readme point to 404s

  #3 opened 5 months ago by developersdigest
  10

• Issues with Multimodal Inference Model Responses

  #44 opened 6 months ago by puar-playground
  3

• Multimodal results for assessing architectural plans

  #45 opened 6 months ago by steveterry66
  1

• troubleshooting chameleon viewer

  #25 opened 6 months ago by jpfraneto
  17

• Questions about image decoder.

  #37 opened 6 months ago by zzzqzhou
  3

• VRAM required for 30B model?

  #43 opened 6 months ago by bryanhpchiang
  1

• Finetuning code

  #42 opened 6 months ago by kalyani7195
  1

• pretraining/finetuning code

  #41 opened 6 months ago by rthapa84
  1

• Poor quality in responses and image recognition

  #38 opened 6 months ago by apresence
  1

• Issue during setup - xformers

  #40 opened 6 months ago by funmonty
  1

• How to run th 7b model on CPU only?

  #5 opened 6 months ago by 0wwafa
  8

• Compatibility issues

  #36 opened 6 months ago by LandoEng
  1

• subprocess.CalledProcessError: Command '['wget', '--continue', '[pre-signed URL]', '-O', 'data/tokenizer/text_tokenizer.json']' returned non-zero exit status 8.

  #29 opened 6 months ago by jsm69
  5

• RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

  #16 opened 6 months ago by nagolinc
  4

• Quantization of models?

  #31 opened 6 months ago by MilanBojic1999
  1

• float32 or float16 versions?

  #35 opened 6 months ago by guii
  1

• 30B Model Single GPU Inference Code Request

  #30 opened 6 months ago by dalan2014
  1

• Download issue:[WinError 2] The system cannot find the file specified

  #34 opened 6 months ago by pydemo
  4

• FileNotFoundError: [WinError 2] The system cannot find the file specified

  #33 opened 6 months ago by pydemo
  0

• Only support text, VQA and Generate picture job are not working

  #23 opened 6 months ago by hellangleZ
  4

• running on windows

  #10 opened 6 months ago by CoffeeShifter
  3

• 30b inference in miniviewer does not work

  #9 opened 6 months ago by lucyknada
  9

• miniViewer Unknown image type error when using drag & drop

  #19 opened 6 months ago by iarata
  1

• What is the function of `<END-OF-TURN>` Token?

  #21 opened 6 months ago by mantle2048
  3

• Report metrics on popular Vision model benchmark

  #12 opened 6 months ago by lucasjinreal
  1

• When can the training code be made public?

  #13 opened 6 months ago by Mr-Harry
  1

• The viewer does not work with the input image using the 7B model.

  #17 opened 6 months ago by chiehpower
  1

• only support localhost could not release as a public

  #18 opened 6 months ago by hellangleZ
  1

• pip install -e . fails due to PEP 660 backend.

  #15 opened 6 months ago by andrewtvuong
  2

• Unknown Image Format Error with Multimodal Input Inference

  #14 opened 6 months ago by iz2late
  1

• How to do inference with 7b

  #7 opened 6 months ago by fahdmirza
  10

• NoneType error for inference and miniviewer

  #4 opened 6 months ago by chihhuiho
  1