s1: Simple test-time scaling

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

Train transformer language models with reinforcement learning.

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

Fully open reproduction of DeepSeek-R1

Repo of "Distillation Quantification for Large Language Models"

📄 A curated list of awesome .cursorrules files

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

基于One API的二次开发版本，仅供个人管理渠道使用，请勿用于商业API分发！

OpenAI 接口接入适配，支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek，等兼容OpenAI接口，仅单可执行文件，配置超级简单，一键部署，开箱即用. Seamlessly integrate with OpenAI and compatible APIs using a single executable for quick setup and depl…

🙌 OpenHands: Code Less, Make More

SWE-bench [Multimodal]: Can Language Models Resolve Real-world Github Issues?

Laminar - open-source all-in-one platform for engineering AI products. Crate data flywheel for you AI app. Traces, Evals, Datasets, Labels. YC S24.

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断

Build your own AI friend

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Examples and guides for using the Gemini API

Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications.

Trans Router

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC…

TEN Agent is a conversational AI powered by the TEN, integrating Gemini 2.0 Live, OpenAI Realtime, RTC, and more. It delivers real-time capabilities to see, hear, and speak, while being fully compa…

Production First and Production Ready End-to-End Keyword Spotting Toolkit

Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding

An extremely fast Python package and project manager, written in Rust.

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…

An open-source RAG-based tool for chatting with your documents.