rawsh

geval

Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment"

mistral.rs

Blazingly fast LLM inference.

MoLE

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

DoRA

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

ARES

alertix

Ticketmaster Sold Out Concert Resale Notification System

inspectus

LLM Analytics

aider

aider is AI pair programming in your terminal

paddler

Stateful load balancer custom-tailored for llama.cpp

burr

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, persist, and execute on your own infrastructure.

Internalize_CoT_Step_by_Step

https://huggingface.co/spaces/yuntian-deng/implicit-cot-math

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

h2ogpt

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://codellama.h2o.ai/

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

repeng

A library for making RepE control vectors

pm4py-core

Public repository for the PM4Py (Process Mining for Python) project.

kserve

Standardized Serverless ML Inference Platform on Kubernetes

ziplm

hatchet

A distributed, fault-tolerant task queue

clustering-benchmarks

Benchmarks `linfa` against `scikit-learn` on a clustering task.

rust-numpy

PyO3-based Rust bindings of the NumPy C-API

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

auto-code-rover

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite with each task costs less than $0.7.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

koboldcpp

A simple one-file way to run various GGML and GGUF models with a KoboldAI UI

GLiNER

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

mupdf.js

JavaScript bindings for MuPDF

DruidJS

A JavaScript Library for Dimensionality Reduction

OpenDevin

🐚 OpenDevin: Code Less, Make More