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

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

React app for inspecting, building and debugging with the Realtime API

Inference and training library for high-quality TTS models.

Retrieval-Augmented Theorem Provers for Lean

The Book of Statistical Proofs

Project Materials for CUHK(SZ) Course CSC4005/MDS6108: Parallel Programming

An Open-Source Package for Information Retrieval

Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

Offline documentation built from official PyTorch release

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

Calculate perplexity on a text with pre-trained language models. Support MLM (eg. DeBERTa), recurrent LM (eg. GPT3), and encoder-decoder LM (eg. Flan-T5).

Instruct-tune LLaMA on consumer hardware

Benchmarking LLM reasoning performance w. chain-of-thought prompting

A simple chatbot starter kit for OpenAI's chat model using Next.js, TypeScript, and Tailwind CSS.

An experimental open-source attempt to make GPT-4 fully autonomous.

⚡ Building applications with LLMs through composability ⚡

ChatGLM-6B：开源双语对话语言模型 | An open bilingual dialogue language model

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

A simple and open-source proxy API that allows you to access OpenAI's ChatGPT API for free!