Stars
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
a toolkit on knowledge distillation for large language models
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model
🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.
项目描述：构建⼀个能够⾃动撰写多模态呈现、具备专业性和深度、数据融合与事实溯源、规范 有逻辑的各类⾦融研报的智能 Agent 系统。 主要负责：根据赛题思路，对目标公司生成金融研报，通过 LLM 获取目标公司的竞争对手，用 akshare 获取数 据源的的三大报表数据，通过 duckduckgo 获取公司信息、行业信息、股份信息等，通过设计数据分析师智能 体，包含三个动作代码生成和执行、收集…
AFAC2025挑战组-赛题三：金融领域中的长思维链压缩-冠军（第一名）解决方案
A modular graph-based Retrieval-Augmented Generation (RAG) system
Implementation of my agent used in 2025 AFAC TianChi competition
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
[COLM’25] DeepRetrieval — 🔥 The First Search Agent Trained by On-Policy Reinforcement Learning
Fully open reproduction of DeepSeek-R1
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
算法岗笔试面试大全，励志做算法届的《五年高考，三年模拟》！
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
A unified evaluation framework for large language models
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。