Thanks to visit codestin.com
Credit goes to github.com

Skip to content

v0.53.1

Latest

Choose a tag to compare

@qaihm-bot qaihm-bot released this 05 May 16:26
· 52 commits to main since this release
a3b8ab0
  • New models

  • Re-instated models

  • Improvements and bug fixes

    • Export metadata.json was missing IO specs for models released as context bin
    • Evaluation bug fixes for huggingface_wavelm_base_plus
    • The model llama_v3_2_3b_instruct_ssd now supports up to 8K context length (thanks to config changes and LM head split out into separate context binary)