m-pedro

cc4e

C Programming for Everybody

NeMo-Aligner

Scalable toolkit for efficient model alignment

EuroSAT

EuroSAT: Land Use and Land Cover Classification with Sentinel-2

GeoTorchAI

GeoTorchAI: A Framework for Training and Using Spatiotemporal Deep Learning Models at Scale

geotorch

Constrained optimization toolkit for PyTorch

bomberland

Bomberland: a multi-agent AI competition based on Bomberman. This repository contains both starter / hello world kits + the engine source code

SWE-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

torax

TORAX: Tokamak transport simulation in JAX

ruff

An extremely fast Python linter and code formatter, written in Rust.

SymbCoT

Codes and Data for ACL 2024 Paper "Faithful Logical Reasoning via Symbolic Chain-of-Thought".

smart

Codebase for ICLR 2023 paper, "SMART: Self-supervised Multi-task pretrAining with contRol Transformers"

mistral-finetune

alpaka

Abstraction Library for Parallel Kernel Acceleration :llama:

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

mteb

MTEB: Massive Text Embedding Benchmark

anthropic-tokenizer-typescript

anthropic-tokenizer

Approximation of the Claude 3 tokenizer by inspecting generation stream

itsdangerous

Safely pass trusted data to untrusted environments and back.

click

Python composable command line interface toolkit

components

Component infrastructure and Material Design components for Angular

angularfire

Angular + Firebase = ❤️

Awesome-SBDD

Papers about Structure-based Drug Design (SBDD)

magenta-studio

Magenta Studio is a collection of music plugins built on Magenta’s open source tools and models

DeepSeek-VL

DeepSeek-VL: Towards Real-World Vision-Language Understanding

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

DeepSeek-LLM

DeepSeek LLM: Let there be answers

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

LiveCodeBench

Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"

OpenCodeInterpreter

OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.