MDK8888/GPTFast

Issues

• Set requirements to more flexible version

  #27 opened 7 months ago by nicolas-dufour
  1

• Help run GPTFast on Mistral-7B-v0.1 (or v.02) for CausalML

  #26 opened 7 months ago by Rinocerbul
  1

• Model Config settings for Llama-based architectures

  #22 opened 8 months ago by jamesoneill12
  8

• Help to run GPTFast on Mixtral-8x7B-Instruct-v0.1

  #25 opened 7 months ago by davideuler
  2

• Update PyTorch to 2.2

  #12 opened 7 months ago by AndreaPi
  2

• Doesn't work on kaggle notebooks - ValueError: Unable to compare versions for numpy>=1.17: need=1.17 found=None. This is unusual. Consider reinstalling numpy.

  #23 opened 8 months ago by c1505
  0

• GPTFast 0.2.1: function argmax_variation() is not used

  #21 opened 8 months ago by alvatar0404
  0

• ERROR: No matching distribution found for triton==2.1.0

  #15 opened 8 months ago by Zephyruss1
  2

• Possible to use with a VL model like LLAVA?

  #16 opened 8 months ago by aliencaocao
  2

• Help to understand

  #14 opened 9 months ago by apirrone
  6