tscohen

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

USACO

Can Language Models Solve Olympiad Programming?

Awesome-LLM-Uncertainty-Reliability-Robustness

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

aideml

AIDE: the Machine Learning CodeGen Agent

InfiniteBench

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

OpenDevin

🐚 OpenDevin: Code Less, Make More

EfficientZero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

MuZero

GPUAR

A CUDA implementation of Arithmetic Coding

LLM-PuzzleTest

This repository is maintained to release dataset and models for multimodal puzzle reasoning.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

vllm

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

CodeXGLUE

CodeXGLUE

MultiPL-E

A multi-programming language benchmark for LLMs

A-Fast-Transformer-based-General-Purpose-LosslessCompressor

This repository contains the source code and dataset link mentioned in WWW 2022 accepted paper "TRACE:A Fast Transformer-based General-Purpose LosslessCompressor".

torchac

Entropy coding / arithmetic coding for PyTorch

Reference-arithmetic-coding

Clear implementation of arithmetic coding for educational purposes in Java, Python, C++.

NeuralCompression

A collection of tools for neural compression enthusiasts.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

branches

Prototype advanced LLM algorithms for reasoning and planning.

lmql

A language for constraint-guided and efficient LLM programming.

guidance

A guidance language for controlling large language models.

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

anthology-of-modern-ml

Collection of important articles to be treated as a textbook

outlines

Structured Text Generation

xlang-paper-reading

Paper collection on building and evaluating language model agents via executable language grounding

code_contests

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

equiformer_v2

[ICLR'24] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

fairscale

PyTorch extensions for high performance and large scale training.