A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

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

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

AWS Deep Learning Containers are pre-built Docker images that make it easier to run popular deep learning frameworks and tools on AWS.

Pipeline Parallelism for PyTorch

This is a pytorch implementation of k-means clustering algorithm

A library for efficient similarity search and clustering of dense vectors.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Transformer related optimization, including BERT, GPT

Parallel S3 and local filesystem execution tool.

A utility tool to create a tarball of existing objects in Amazon S3

Crosslingual Generalization through Multitask Finetuning

Fast & Simple repository for pre-training and fine-tuning T5-style models

🦜🔗 Build context-aware reasoning applications

The official GitHub page for the survey paper "A Survey of Large Language Models".

A StockX, FlightClub, Goat, and Stadium Goods API all in one. This sneaker API allows users to search sneakers and track and compare prices while providing additional info such as product links and…

A method for event correlation detection based on Spatial-Temporal-Textual point process

NLP, before and after spaCy

🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Minimal keyword extraction with BERT