modelscope / ms-swiftLinks
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, Phi4, ...) (AAAI 2025).
☆10,533Updated this week
Alternatives and similar repositories for ms-swift
Users that are interested in ms-swift are comparing it to the libraries listed below
Sorting:
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,170Updated this week
- A Next-Generation Training Engine Built for Ultra-Large MoE Models☆4,937Updated this week
- Retrieval and Retrieval-augmented LLMs☆10,694Updated last week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,174Updated this week
- Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、…☆6,573Updated 11 months ago
- [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☆9,352Updated last month
- GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型☆6,896Updated 3 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆3,836Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆8,180Updated 2 weeks ago
- The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.☆6,301Updated last year
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆12,038Updated 3 weeks ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆14,368Updated last week
- A series of large language models developed by Baichuan Intelligent Technology☆4,121Updated 11 months ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆60,475Updated this week
- 中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3☆1,945Updated last year
- Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks☆3,216Updated this week
- 复现大模型相关算法及一些学习记录☆2,326Updated 3 weeks ago
- Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷☆5,359Updated this week
- Reproduce R1 Zero on Logic Puzzle☆2,407Updated 7 months ago
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking☆1,827Updated this week
- 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。☆4,146Updated last month
- InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions☆2,899Updated 4 months ago
- Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you ne…☆8,632Updated last week
- ☆1,080Updated last month
- 中文nlp解决方案(大模型、数据、模型、训练、推理)☆3,672Updated 2 months ago
- MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios☆3,514Updated last week
- Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).☆7,075Updated 2 months ago
- 用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.☆2,862Updated last year
- LLM&VLM Tutorial☆1,890Updated 5 months ago
- ReLE中文大模型能力评测（持续更新）：目前已囊括291个大模型，覆盖chatgpt、gpt-5、o4-mini、谷歌gemini-2.5、Claude4、智谱GLM-Z1、文心一言、qwen-max、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及…☆4,987Updated last week