erfanzar/EasyDeL

Issues

• There is some issue with trainer , loss gets to zero after 1 epoch full fine tuning.

  #177 opened 6 days ago
  6

• Examples and Docs to demonstrate running inferencing using Llama-3.2-1b or 3b models on TPU V4

  #176 opened 15 days ago
  1

• Inference is very slow on an TPU v4 instance - 2 Tokens / Sec

  #175 opened 15 days ago
  7

• Received an error while using pipeline generation using llama model

  #174 opened 21 days ago
  1

• DPO trainer example

  #172 opened a month ago
  12