Skip to content

v0.3.2

Latest
Compare
Choose a tag to compare
@li-plus li-plus released this 24 Apr 08:20
· 2 commits to main since this release
a46f474
  • Support p-tuning v2 finetuned models for ChatGLM family
  • Fix convert.py for lora models & chatglm3-6b-128k
  • Fix RoPE theta config for 32k/128k sequence length
  • Better cuda cmake script respecting nvcc version