ModelScope
Change the repository type filter
All
Repositories list
41 repositories
- 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).
- A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
- ReMe: Memory Management Framework for Agents - Remember Me, Refine Me.
RM-Gallery
Public- Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
modelscope
PublicModelScope: bring the notion of Model-as-a-Service to life.- MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios
- a toolkit on knowledge distillation for large language models
DiffSynth-Engine
Publicmodelscope-studio
PublicA third-party component library based on Gradio. Integrates Ant Design, Ant Design X, and more advanced components to help you build applications efficiently.FunASR
PublicA Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.modelscope-classroom
PublicMCPBench
Public- An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
- A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
dash-infer
PublicDashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.Nexus-Gen
PublicFunClip
PublicOpen-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.Katz
Public[ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.mcp-central
Publicscepter
PublicSCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.