The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

Evaluation of the Open-Assistant language models

A framework for the evaluation of autoregressive code generation language models.

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Fine-tuning LLaMA to follow instructions within 1 Hour and 1.2M Parameters

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

The current release is only for M1 and M2 macs. We are working on Intel Mac and Windows support. Soon we'll release for all the platforms.

Train transformer language models with reinforcement learning.

Alpaca-LoRA as Chatbot service

This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as Flan-T5.

A framework for few-shot evaluation of autoregressive language models.

Plug and play modules to optimize the performances of your AI systems 🚀

Instruct-tune LLaMA on consumer hardware

Alpaca dataset from Stanford, cleaned and curated

Locally run an Instruction-Tuned Chat-Style LLM

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

The simplest way to run LLaMA on your local machine

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

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

Quantized inference code for LLaMA models

Repo for fine-tuning GPTJ and other GPT models

Unishop MonoToMicro Workshop

Official release of the ProGen models

a Transformer-based neural network for generating highly optimized protein sequences called Regularized Latent Space Optimization (RELSO)

Explore vector similarity in Redis

Conditional Transformer Language Model for Controllable Generation