Reinforcement Learning
Safetensors
English
qwen3_5_text
tmax
terminal-agent

Commit History

3 days ago

  1. Credit the original training dataset paper with its BibTeX citation

    Verified signature
    c02f0d9
  2. Remove Ai2 attribution and responsible-use sentence from v1.1 model card

    Verified signature
    fde5022

6 days ago

  1. Use GPU-tested vLLM 0.32.0 serving command

    Verified signature
    3eafde6
  2. Link TMax v1.1 datasets and collection under TMaxxx

    Verified signature
    4507a07
  3. Update TMax v1.1 repository names and links

    Verified signature
    3efa941

  1. Release TMax v1.1; TB-Lite winner step 100

    Verified signature
    eefc819
  2. Preserve original checkpoint LFS pointer sizes

    117aef3
  3. Copy files from models/TMaxxx/qwen35-9b-dppo-litecoder-sc3

    Verified signature
    5c99fde

  1. initial commit

    Verified signature
    a531ace