Gemini Multimodal Live + WebRTC in a single `app.ts`

Build resilient language agents as graphs.

nanoGPT style version of Llama 3.1

A native PyTorch Library for large model training

Robust recipes to align language models with human and AI preferences

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

Manage scalable open LLM inference endpoints in Slurm clusters

🤖 Build voice-based LLM agents. Modular + open source.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Print-friendly, minimalist CV page

Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors

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

Go ahead and axolotl questions

Just a bunch of benchmark logs for different LLMs

Reference implementation of Mistral AI 7B v0.1 model.

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-l…

This repository implements the chain of verification paper by Meta AI

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Hackable and optimized Transformers building blocks, supporting a composable construction.

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Generative Agents: Interactive Simulacra of Human Behavior

Fast and memory-efficient exact attention

⚡ Building applications with LLMs through composability ⚡

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology