PinnedLoading

1. nanoRLHFnanoRLHFPublic

   RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.

   Python 46 9

2. vecparservecparserPublic

   Vectorize the Matlab/CVX for-loops as much as possible.

   Python 5 1

3. bert-chunkerbert-chunkerPublic

   bert-chunker: efficient and trained chunking for unstructured documents. 训练Bert做文档分段.

   Python 4 1

4. Proactive-Sales-AgentProactive-Sales-AgentPublic

   Proactive LLM sales agent server. 主动销售的大模型销售Agent服务器。

   Python 6 1

5. cvx-codercvx-coderPublic

   LLM good at answering questions and coding about Matlab CVX. 微调大模型写CVX代码，回答CVX问题。

   1