Stars
Vector (and Scalar) Quantization, in Pytorch
ContextGem: Effortless LLM extraction from documents
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Fully open data curation for reasoning models
Task-Aware Agent-driven Prompt Optimization Framework
Solve Visual Understanding with Reinforced VLMs
A fork to add multimodal model training to open-r1
verl: Volcano Engine Reinforcement Learning for LLMs
Democratizing Reinforcement Learning for LLMs
Fully open reproduction of DeepSeek-R1
Awesome-RAG: Collect typical RAG papers and systems.
An open source implementation of CLIP.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
Must-read Papers on Knowledge Editing for Large Language Models.
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
DSPy: The framework for programming—not prompting—language models
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
📝 An Awesome Collection of Chinese Legal Dataset and Relevant Resources. 致力于收集全面的中文法律数据源
③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.