Question and Answer based on Anything.

Universal LLM Deployment Engine with ML Compilation

Faster Whisper transcription with CTranslate2

one-click face swap

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

A modular graph-based Retrieval-Augmented Generation (RAG) system

“让爷康康”是一款手机 AI 应用程序，可以监测不良坐姿并进行语音提示

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Multilingual Voice Understanding Model

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

Fast lexical search library implementing BM25 in Python using Numpy and Scipy

Official implementation of paper How to Understand Whole Repository? New SOTA on SWE-bench Lite (21.3%)

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

Self-Alignment with Principle-Following Reward Models

LLM training in simple, raw C/CUDA

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

⚡FlashRAG: A Python Toolkit for Efficient RAG Research

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Build resilient language agents as graphs.

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)