Stars
Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.
Persist and reuse KV Cache to speedup your LLM.
GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters
RubikSQL: Bridging the NL2SQL Research-to-Production Gap via Lifelong Learning Agentic Knowledge Base
A powerful VS Code extension for real-time Jinja2 template preview with authentic Python Jinja2 (via Pyodide). Edit templates and variables side-by-side with instant rendering, markdown support, me…
Python disk-backed cache (Django-compatible). Faster than Redis and Memcached. Pure-Python.
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
🐎 A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure. (Python wrapper for daachorse)
An open protocol enabling communication and interoperability between opaque agentic applications.
The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.
No fortress, purely open ground. OpenManus is Coming.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
FIT: 企业级AI开发框架，提供多语言函数引擎（FIT）、流式编排引擎（WaterFlow）及Java生态的LangChain替代方案（FEL）。原生/Spring双模运行，支持插件热插拔与智能聚散部署，无缝统一大模型与业务系统。
Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".
Code for the paper "Evaluating Large Language Models Trained on Code"
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Implementation of disco-diffusion wrapper that could run on your own GPU with batch text input.
PyTorch code for "EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer" (ECCV 2022)
Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.