Stars
The official Python client to connect with ModelScope Hub.
Ultron: Collective Intelligence System — Shared Memories, Skills, and Harnesses Across Every Agent
Jintao-Huang / mcore-bridge
Forked from modelscope/mcore-bridgeMCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large language models and making Megatron training as simple as Transformers.
The source code for: https://modelscope.github.io/sirchmunk-web/
Skill optimization framework for LLMs — evolve system prompts via textual gradient descent with beam search, human-in-the-loop annotation, and DPO preference data export.
MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models (Qwen3…
Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.
🐿️ Sirchmunk: Raw data to self-evolving intelligence, real-time.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Twinkle✨: Training workbench to make your model glow.
SGLang is a high-performance serving framework for large language models and multimodal models.
A modular and stable agent sandbox runtime environment.
MiniMax-M2, a model built for Max coding & agentic workflows.
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Fully Open Framework for Democratized Multimodal Training
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Train transformer language models with 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
Local UI to run and train LLMs and diffusion models, including Kimi K3, MiniMax-H3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).