WHAT NEW IN X11.03 TUE

X 上的 AI 合集档案 · 22 个合集 · 65,263 条

agentVIDEO

Repo2RLEnv 发布 TaskSmith 与 50 个 RL 环境

Hugging Face 的 Repo2RLEnv 上线 TaskSmith,可把已合并 PR 转成可验证 RL 环境,并放出 50 个来自 Transformers、TRL 等仓库的任务。

Sergio Paniego
@SergioPaniego26 天前收录原推发布于 2026.10.06
Sergio Paniego @SergioPaniego原推发布于 2026.10.06
在 X 上打开原推

Repo2RLEnv just shipped TaskSmith + 50 high quality RL envs generated from HF repos 🔨 TaskSmith is a specialized harness that turns a merged PR into a verified RL env the envs come from HF repos (Transformers, TRL, PEFT, Accelerate, Diffusers), shipped as Harbor tasks you can eval or train on > code: http://github.com/huggingface/Repo2RLEnv > dataset: http://huggingface.co/datasets/FineEnvs/HF_ML_Tasksmith

x.com/sergiopaniego/status/2107478232656183509采集于 2026.10.07 10:24