提交历史

作者 SHA1 备注 提交日期
  Tobi Lutke 9b3a209a97 Fix GRPO training: apply chat template to prompts 4 月之前
  Tobi Lutke 891f3262cf Fix GRPO reward function to handle think blocks and end tokens 4 月之前
  Tobi Lutke 8a1c4cdab0 Add 1.7B and 4B GRPO training and GGUF conversion scripts 4 月之前