High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

💡 dokieli is a clientside editor for decentralised article publishing, annotations and social interactions

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

Improved file parsing for LLM’s

GoNB, a Go Notebook Kernel for Jupyter

DSPy: The framework for programming—not prompting—foundation models

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

InstructLab Command-Line Interface. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.

Steering Llama 2 with Contrastive Activation Addition

This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).

Official repo for the paper "Weight-based Decomposition: A Case for Bilinear MLPs"

Explore the Limits of Omni-modal Pretraining at Scale

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework Join our Community: https://discord.com/servers/agora-999382051935506503

Python bindings for llama.cpp

The Abstraction and Reasoning Corpus

Implementation for MatMul-free LM.

Diffusion on syntax trees for program synthesis

Code and implementations for the paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Structured Text Generation

Code for reproducing our paper "Not All Language Model Features Are Linear"

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arxiv.org/abs/2205.09726).

Please see the readme file as well as our 2019 EMNLP paper linked here -->

customizable template GPT code designed for easy novel architecture experimentation

port of Andrjey Karpathy's llm.c to Mojo