注册并分享邀请链接,可获得视频播放与邀请奖励。

Ben Burtenshaw
@ben_burtenshaw
community MLE 🤗 @huggingface gh/hf username: burtenshaw anon feedback:
加入 February 2024
732 正在关注    10.4K 粉丝
You can now train an open model with RL inside claude code, codex, opencode, pi, or any harness you need. All at once, with the harness runs unmodified. @adithya_s_k added a capture proxy to openenv. it sits between the harness and the model and records the exact token ids and logprobs of every call. to the harness it's just another model provider. harbor supplies the tasks and sandboxes, trl trains with async GRPO. it's worth doing because the harness completely changes what the model learns. the same LFM2.5-2.6B weights solve 62% of held-out tasks in mini-swe-agent and 33% in claude code. after RL across four harnesses the average goes from 42% to 54%, and claude code from 33% to 49%. there are three envs you can try in the browser and a training script for each. guide:
显示更多
0
21
181
21
转发到社区