Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

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

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

A framework for few-shot evaluation of language models.

The official evaluation suite and dynamic data release for MixEval.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Official repository for ORPO

The official implementation of Self-Play Fine-Tuning (SPIN)

⚗️ AI Feedback framework for scalable LLM alignment

A question-answering dataset with a focus on subjective information

Google Research

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Train transformer language models with reinforcement learning.

Code accompanying the paper Pretraining Language Models with Human Preferences

Code and documentation to train Stanford's Alpaca models, and generate the data.

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Failure archive for ChatGPT and similar models

Experiments with generating opensource language model assistants

Aligning pretrained language models with instruction data generated by themselves.

⚡ Building applications with LLMs through composability ⚡