kaiokendev

vllm

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

outlines

Structured Text Generation

cp-algorithms

Algorithm and data structure articles for https://cp-algorithms.com (based on http://e-maxx.ru)

LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

unit

Next Generation Visual Programming System

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

long_llama

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

yarn

YaRN: Efficient Context Window Extension of Large Language Models

reliableGPT

Get 100% uptime, reliability from OpenAI. Handle Rate Limit, Timeout, API, Keys Errors

lorahub

[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

LongChat

Official repository for LongChat and LongEval

QuIP

Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"

H2O

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

rerope

Rectified Rotary Position Embeddings

BLoRA

batched loras

VerseProgrammingLanguage

Verse Programming Language - Functional logic language developed by Epic Games - all informations, official resources and snippets

TransnormerLLM

Official implementation of TransNormerLLM: A Faster and Better LLM

NeuScraper

[ACL 2024] This is the code repo for our ACL’24 paper "Cleaner Pretraining Corpus Curation with Neural Web Scraping".

PoSE

Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)

Copyisallyouneed

[ICLR 2023] Codebase for Copy-Generator model, including an implementation of kNN-LM

CSRGraph

A tiny library for large graphs

Formal-LLM

Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents

Attention-Transition

Empower Your Model with Longer and Better Context Comprehention

transformer_in_transformer

dropbp

The official code for Dropping Backward Propagation (DropBP)

LuckyMera

smolbbs

Lightweight single-threaded textboard made in PHP 7.4. Uses JSON for data storage and retrieval. No database / DB required!

residualstream

unitaryPE

Algebraic Positional Encodings