Stars
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
🚀 Efficient implementations of state-of-the-art linear attention models
Korean MTEB Retrieval Evaluators for SPLADE, Dense, and Reranking models
Supercharge Your LLM with the Fastest KV Cache Layer
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
🚀 PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍
Detection and automatic updating of Korean datasets uploaded to Hugging Face
Development repository for the Triton language and compiler
A framework for few-shot evaluation of language models.
A performance library for machine learning applications.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
nanorlhf: from-scratch journey into how LLMs and RLHF really work.
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Multilingual Voice Understanding Model
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Use openvoice v2 module to do real time tts(text to speech) task for on-device robotics. Trying to inference the model on single board like raspberry pi, jetson boards.
Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
Version of Kokoro-TTS accelerated on Apple Silicon