代码库
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
Python
evaluationllmperformanceragvlm
Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.
Python
A modular and stable agent sandbox runtime environment.
Python
Enjoy the magic of Diffusion models!
Python
Collect every awesome work about r1!
Python
collectiondeepseekgrpoo1qwenr1reasoningrl
🐿️ Sirchmunk: Raw data to self-evolving intelligence, real-time.
Python
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
Python
gradiogradio-python-llmllmspeech-recognitionspeech-to-textsubtitles-generatorvideo-clipvideo-subtitles
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Python
audio-visual-speech-recognitionconformerdfsmnparaformerpretrained-modelpunctuationpytorchrnntspeaker-diarizationspeech-recognitionspeechgptspeechllmvadvoice-activity-detectionwhisper
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Python
deepseek-r1embeddinggrpointernvlligerllamallama4llmloramegatronmoemultimodalopen-r1peftqwen3qwen3-6qwen3-omniqwen3-vlrerankersft
MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers.
Python
deepseek-r1glm-5gpt-ossllama4llmloramegatronminimaxms-swiftpeftqwen3-5qwen3-omniqwen3-vltransformers