strngelet

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

llama2.c

Inference Llama 2 in one file of pure C

codellama

Inference code for CodeLlama models

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

mistral-inference

Official inference library for Mistral models

llama2.mojo

Inference Llama 2 in one file of pure 🔥

yarn

YaRN: Efficient Context Window Extension of Large Language Models

Pai-Megatron-Patch

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

vercel-ai-chatbot

A full-featured, Supabaseified Next.js AI chatbot built by Vercel Labs & Supabase

fastT5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

RASP

An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

LongAlign

[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs

INTERS

This is the repository for our paper "INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning"

LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

detect-pretrain-code-contamination

GPT4-Vision-React-Starter

Early Alpha Release: Chat with Your Image - Leveraging GPT-4 Vision and Function Calls for AI-Powered Image Analysis and Description