SsmallSong

YuLan-Mini

A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.

alignment-handbook

Robust recipes to align language models with human and AI preferences

FlashRAG

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

Leetcode-Solution-All

1000篇通俗易懂且高质量的 LeetCode 解析，动画题解，套路分析，模板分享

LESS

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

OpenCoder-llm

openrlhf

ProLong

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

RAGEN

RAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.

TRL_FT

This repository is used for studying reinforcement learning and fine-tuning large models.

SsmallSong/TRL_FT

This repository is used for studying reinforcement learning and fine-tuning large models.

SsmallSong/alignment-handbook

Robust recipes to align language models with human and AI preferences

SsmallSong/FlashRAG

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

SsmallSong/Leetcode-Solution-All

1000篇通俗易懂且高质量的 LeetCode 解析，动画题解，套路分析，模板分享

SsmallSong/LESS

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

SsmallSong/OpenCoder-llm

SsmallSong/openrlhf

SsmallSong/ProLong

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

SsmallSong/RAGEN

RAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.

SsmallSong/simpo

SsmallSong/test

SsmallSong/ResearchFigure

Some example codes for drawing figures in research paper

SsmallSong/resume

An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git

SsmallSong/ruc_gsai_rl

这是**人民大学高瓴人工智能学院本科课程《强化学习》的期末项目安排，项目内容是训练一个适用于国标麻将的强化学习智能体。

SsmallSong/sd-webui-controlnet

WebUI extension for ControlNet

SsmallSong/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs