ModelScope

All

41 repositories

data-juicer
Public
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
data-science data data-visualization data-analysis data-processing multi-modal data-pipeline synthetic-data pre-training foundation-models
Python
•
Apache License 2.0
•258•5k•44•24•Updated Aug 10, 2025Aug 10, 2025
ms-swift
Public
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4v, Phi4, ...) (AAAI 2025).
deploy llama lora embedding omni liger peft multimodal sft megatron
Python
•
Apache License 2.0
•806•9.2k•784•22•Updated Aug 10, 2025Aug 10, 2025
modelscope-mcp-server
Public
ModelScope MCP Server (in active development)
agent mcp aigc llm modelscope mcp-server fastmcp
Python
•
Apache License 2.0
•2•6•0•0•Updated Aug 9, 2025Aug 9, 2025
DiffSynth-Studio
Public
Enjoy the magic of Diffusion models!
Python
•
Apache License 2.0
•862•9.4k•153•3•Updated Aug 8, 2025Aug 8, 2025
DiffSynth-Engine
Public
Python
•
Apache License 2.0
•21•196•5•0•Updated Aug 8, 2025Aug 8, 2025
Trinity-RFT
Public
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
agent llm rlhf
Python
•
Apache License 2.0
•25•218•7•4•Updated Aug 8, 2025Aug 8, 2025
evalscope
Public
A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
performance evaluation vlm rag llm
Python
•
Apache License 2.0
•163•1.5k•81•2•Updated Aug 8, 2025Aug 8, 2025
ms-agent
Public
MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration
agent data-science code chatbot multi-agents rag gpts llm multimodal-large-language-models qwen
Python
•
Apache License 2.0
•384•3.3k•76•4•Updated Aug 8, 2025Aug 8, 2025
RM-Gallery
Public
A One-Stop Reward Model Platform
Python
•
Apache License 2.0
•3•61•2•0•Updated Aug 8, 2025Aug 8, 2025
3D-Speaker
Public
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
speaker-verification speaker-diarization language-identification voxceleb modelscope campplus eres2net 3d-speaker cnceleb sdpn
Python
•
Apache License 2.0
•199•2.3k•4•1•Updated Aug 7, 2025Aug 7, 2025
agentscope
Public
Start building LLM-empowered multi-agent applications in an easier way.
agent drag-and-drop mcp chatbot multi-agent multi-modal distributed-agents gpt-4 large-language-models llm
Python
•
Apache License 2.0
•467•7.7k•56•20•Updated Aug 7, 2025Aug 7, 2025
modelscope
Public
ModelScope: bring the notion of Model-as-a-Service to life.
nlp science cv speech multi-modal python machine-learning deep-learning
Python
•
Apache License 2.0
•853•8.2k•10•4•Updated Aug 7, 2025Aug 7, 2025
dash-infer
Public
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
cpu cuda llm llm-inference native-engine guided-decoding
C
•
Apache License 2.0
•28•264•7•0•Updated Aug 6, 2025Aug 6, 2025
FunASR
Public
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
pytorch speech-recognition vad punctuation whisper audio-visual-speech-recognition speaker-diarization voice-activity-detection conformer pretrained-model
Python
•
MIT License
•1.2k•12k•406•11•Updated Aug 5, 2025Aug 5, 2025
modelscope-classroom
Public
Jupyter Notebook
•
Apache License 2.0
•119•1k•2•0•Updated Jul 31, 2025Jul 31, 2025
Nexus-Gen
Public
Python
•
Apache License 2.0
•14•262•14•0•Updated Jul 29, 2025Jul 29, 2025
ClearerVoice-Studio
Public
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
audio deep-learning speech pytorch speech-separation speech-enhancement noise-suppression speaker-extraction bandwidth-extension speech-quality-evaluation
Python
•
Apache License 2.0
•257•3.2k•58•5•Updated Jul 28, 2025Jul 28, 2025
modelscope-studio
Public
A third-party component library based on Gradio.
python ui gradio ant-design modelscope gradio-custom-component ant-design-x
TypeScript
•
Apache License 2.0
•16•111•3•0•Updated Jul 28, 2025Jul 28, 2025
easydistill
Public
a toolkit on knowledge distillation for large language models
knowledge-distillation large-language-models
Python
•
Apache License 2.0
•11•134•3•0•Updated Jul 28, 2025Jul 28, 2025
FunClip
Public
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
speech-recognition speech-to-text gradio video-clip subtitles-generator video-subtitles llm gradio-python-llm
Python
•
MIT License
•568•4.8k•35•0•Updated Jul 11, 2025Jul 11, 2025
facechain
Public
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
Jupyter Notebook
•
Apache License 2.0
•888•9.5k•17•3•Updated Jun 6, 2025Jun 6, 2025
Trinity-Studio
Public
JavaScript
•
Apache License 2.0
•0•6•0•0•Updated May 26, 2025May 26, 2025
Katz
Public
[ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.
inference lora model-serving diffusion-model controlnet sdxl
Python
•
Apache License 2.0
•1•9•0•0•Updated May 26, 2025May 26, 2025
MCPBench
Public
The evaluation benchmark on MCP servers
benchmark database mcp websearch mcp-server
Python
•
Apache License 2.0
•9•170•6•0•Updated May 21, 2025May 21, 2025
mcp-central
Public
Collection of model-centric MCP servers
Python
•
Apache License 2.0
•2•21•4•0•Updated May 21, 2025May 21, 2025
awesome-deep-reasoning
Public
Collect every awesome work about r1!
collection rl reasoning r1 o1 qwen deepseek grpo
Python
•13•405•0•0•Updated May 2, 2025May 2, 2025
ImagePulse
Public
Open Image Curation Tools
Python
•
Apache License 2.0
•2•41•0•0•Updated Apr 22, 2025Apr 22, 2025
scepter
Public
SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.
generative-model scedit aigc lar-gen stylebooth
Python
•
Apache License 2.0
•30•534•27•1•Updated Apr 3, 2025Apr 3, 2025
PromptScope
Public
Enjoy easier conversations with LLM
prompt multi-modal gpt-4 in-context-learning large-language-models prompt-engineering llms
Python
•
Apache License 2.0
•5•42•3•0•Updated Mar 13, 2025Mar 13, 2025
r-chain
Public
Python
•
Apache License 2.0
•4•12•0•0•Updated Mar 10, 2025Mar 10, 2025