A c/c++ implementation of micrograd: a tiny autograd engine with neural net on top.

Video+code lecture on building nanoGPT from scratch

The official PyTorch implementation of Google's Gemma models

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

The development repository for LessWrong2 and the EA Forum, based on Vulcan JS

ReLM is a Regular Expression engine for Language Models

Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Python package for easily interfacing with chat apps, with robust features and minimal code complexity.

TART: A plug-and-play Transformer module for task-agnostic reasoning

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Numbers every LLM developer should know

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

😎 Awesome list of tools and projects with the awesome LangChain framework

LLM training code for Databricks foundation models

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

Universal LLM Deployment Engine with ML Compilation

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Simple transformer implementation from scratch in pytorch.

StableLM: Stability AI Language Models

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

Robust Speech Recognition via Large-Scale Weak Supervision

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[SIGIR 2022] CenterCLIP: Token Clustering for Efficient Text-Video Retrieval. Also, a text-video retrieval toolbox based on CLIP + fast pyav video decoding.

Adding guardrails to large language models.

🦜🔗 Build context-aware reasoning applications