A high-throughput and memory-efficient inference and serving engine for LLMs

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

aarch64 for bitsandbytes

Instruct-tune LLaMA on consumer hardware

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Port of Facebook's LLaMA model in C/C++

This repo includes ChatGPT prompt curation to use ChatGPT better.

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

CLIP+MLP Aesthetic Score Predictor

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Large-scale pretraining for dialogue

A modular RL library to fine-tune language models to human preferences

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Tools and Modeling Code for the MASSIVE dataset

An open source implementation of CLIP.

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Pretrained language model with 100B parameters

Example models using DeepSpeed

Huggingface Transformers + Adapters = ❤️

Language Models Can See: Plugging Visual Controls in Text Generation

Facebook Low Resource (FLoRes) MT Benchmark

Prefix-Tuning: Optimizing Continuous Prompts for Generation

A Python module to bypass Cloudflare's anti-bot page.

[NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features

UniLM AI - Unified "Language" Model Pre-training across Tasks, Languages, and Modalities

古文语言理解测评基准 Classical Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard