mlmabie

pyreft

ReFT: Representation Finetuning for Language Models

cover-agent

CodiumAI Cover-Agent: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞

pareas

GPU-accelerated compiler

neuromancer

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

gooey-gui

Scaleable, production grade web apps in pure Python (& powering Gooey.AI)

executorch

On-device AI across mobile, embedded and edge for PyTorch

apl-md

LLM_MultiAgents_Survey_Papers

Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Tsunami

pipeline to auto (scrape => clean => analyze => chat with) tons of data

openui

OpenUI let's you describe UI using your imagination, then see it rendered live.

nobuild

Header only library for writing build recipes in C.

efficient-kan

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

maestro

A framework for Claude Opus to intelligently orchestrate subagents.

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

turing

Turing machines, Rule 110, and A::B reversal using Claude 3 Opus.

JetStream

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

evals

Using various instructor clients evaluating the quality and capabilities of extractions and reasoning.

marker

Convert PDF to markdown quickly with high accuracy

llm.c

LLM training in simple, raw C/CUDA

challenge-001-exemplar

Challenge Problem #1 - Linux Kernel (NOTE: This code does not reflect the active state of what will be used at competition time, please refer to resources inside of the competition environment)

recipes

This repository shares end-to-end notebooks on how to use various features and integrations with Weaviate at the core!

notebooks

Code examples and jupyter notebooks for the Cohere Platform

langgraph

Build resilient language agents as graphs.

llm-command-r

Access the Cohere Command R family of models

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 1.5 minutes to run.

long-form-factuality

Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

llm_split_recall_test

Split and Recall: A simple and efficient benchmark to evaluate in-context recall performance of Large Language Models (LLMs)

surya

OCR, layout analysis, reading order, line detection in 90+ languages

lumentis

AI powered one-click comprehensive docs from transcripts and text.