[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

The Largest-scale Chinese Medical QA Dataset： with 26,000,000 question answer pairs.

A self-extracting archiving tool for Unix systems, in 100% shell script.

使用多轮对话数据集对deepseek进行lora微调教程

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

Tools for merging pretrained large language models.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Olivar: towards automated variant aware primer design for multiplex tiled amplicon sequencing of pathogens

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

中文nlp解决方案(大模型、数据、模型、训练、推理)

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

ModelScope: bring the notion of Model-as-a-Service to life.

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

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…

Neo4j GraphRAG for Python

A modular graph-based Retrieval-Augmented Generation (RAG) system

Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

A collection project that uses graph technology

基于大模型+知识图谱的知识库问答

A modular graph-based Retrieval-Augmented Generation (RAG) system

本库收录的是《GraphRAG实战》一书的开源资源，包括引用资料、图片、代码和样章等。

基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了LLaMA-Factory用于训练，fastllm和vllm用于推理，

code for idle-universe