Teutonic-I Reliquary RL 最新检查点镜像发布
原标题:ReliquaryForge/Teutonic-I-Reliquary-RL
AI 摘要
Hugging Face 上发布了 ReliquaryForge/Teutonic-I-Reliquary-RL,这是 Bittensor 子网 81(Reliquary)上异步强化学习运行 teutonic-rl-async-v1 的最新检查点(版本 157)。该 9B 模型基于 Teutonic-I-Reliquary-SFT 做 RL 训练,rollout 由子网矿工生成并验证。仓库由验证者自动镜像,附带签名索引与权重哈希,供矿工直接下载最新权重。
正文节选
--- license: apache-2.0 library_name: transformers pipeline_tag: text-generation base_model: - ReliquaryForge/Teutonic-I-Reliquary-SFT tags: - teutonic - bittensor - reinforcement-learning - reliquary --- # Teutonic-I Reliquary RL (live checkpoint) Latest checkpoint of the live asynchronous RL run **`teutonic-rl-async-v1`** on Bittensor subnet 81 (Reliquary): Teutonic-I 9B trained with RL from **`ReliquaryForge/Teutonic-I-Reliquary-SFT@18dfb97d`**, on rollouts generated and verified by the sub