lnx

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

haentgl

MySQL proxies for Serverless and Cloud.

generative-recommenders

Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

LLM101n

LLM101n: Let's build a Storyteller

RecommenderSystem

llm.c

LLM training in simple, raw C/CUDA

semantic-router

Superfast AI decision making and intelligent processing of multi-modal data.

1brc

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

crabml

a fast cross platform AI inference engine 🤖 using Rust 🦀 and WebGPU 🎮

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

dspy

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

CUDA_Freshman

fastai

The fastai deep learning library

bert_score

BERT score for text generation

spaCy

💫 Industrial-strength Natural Language Processing (NLP) in Python

flameshow

A terminal Flamegraph viewer.

vllm

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

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

text-generation-webui

A Gradio web UI for Large Language Models.

candle

Minimalist ML framework for Rust

lm-evaluation-harness

A framework for few-shot evaluation of language models.

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Chinese-LLaMA-Alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

llama

Inference code for Llama models

llama2.c

Inference Llama 2 in one file of pure C

pgrx

Build Postgres Extensions with Rust!

TurboPFor-Integer-Compression

Fastest Integer Compression

streamvbyte

Fast integer compression in C using the StreamVByte codec