Alpha-VLLM/Lumina-mGPT

Issues

• VQGAN weights not found and WeChat group QR code expired

  #22 opened 7 days ago by bollossom
  1

• cannot generate 256*256 images?

  #20 opened 9 days ago by zhangzheyu0
  1

• Plan to open source the training data or data processing script?

  #21 opened 11 days ago by densechen
  1

• VQGAN models dont exist

  #5 opened 17 days ago by gjnave
  1

• Trainable Parameters and their precisions

  #17 opened 17 days ago by SxJyJay
  1

• can lumina-mgpt support inference speed up project such as vllm

  #19 opened 19 days ago by yyyouy
  1

• problem with Image editing

  #16 opened 25 days ago by chkmook
  2

• Save ckpt error

  #18 opened 23 days ago by SxJyJay
  3

• WeChat链接更新

  #12 opened a month ago by BeBuBu
  2

• Training Scrip Error: AttributeError: 'ChameleonRMSNorm' object has no attribute 'reset_parameters'. Did you mean: 'get_parameter'?

  #14 opened a month ago by SunzeY
  5

• Code for fine-tuning Chameleon

  #15 opened a month ago by Johanan528
  0

• Potential bug on z-loss calculation

  #13 opened a month ago by leloykun
  6

• 3 x Black and White output

  #11 opened a month ago by Excidos
  5

• flash_attn_2_cuda error

  #9 opened a month ago by abrakjamson
  2

• Encoding error reading text_tokenizer.json

  #2 opened a month ago by throttlekitty
  2

• Has the lumina-mGPT done any quantitative evaluation on generation or VLM benchmark?

  #7 opened a month ago by muxizju
  1

• what is the memory requirement to run Lumina-mGPT

  #1 opened a month ago by ninjasaid2k
  1

• Gradio launches public/live by default

  #3 opened a month ago by throttlekitty
  2

• Link to 34B model leads to 404 page

  #4 opened a month ago by RandomInternetPreson
  3

• What is the scale of the training data, training machine and training time for the 7B and 30B model

  #6 opened a month ago by zhengyunqq
  0