mastane

llm-colosseum

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

grok-1

Grok open release

FastEval

Fast & more realistic evaluation of chat language models. Includes leaderboard.

ReProver

Retrieval-Augmented Theorem Provers for Lean

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

RAIN

[ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning

lean-gym

mathlib4

The math library of Lean 4

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

LLaMA-Pro

[ACL 2024] Progressive LLaMA with Block Expansion.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

minigo

An open-source implementation of the AlphaGoZero algorithm

proximal

Sample implementations of proximal operators

bagel

A bagel, with everything.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

deep-learning-pytorch-huggingface

FastUI

Build better UIs faster.

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

lean-liquid

💧 Liquid Tensor Experiment

LeanCopilot

LLMs as Copilots for Theorem Proving in Lean

LeanDojoChatGPT

ChatGPT plugin for theorem proving in Lean

lean-premise-selection

llmstep

llmstep: [L]LM proofstep suggestions in Lean 4.

naturalprover

NaturalProver: Grounded Mathematical Proof Generation with Language Models

mathlib

Lean 3's obsolete mathematical components library: please use mathlib4

lean-perfectoid-spaces

A formalization of the concept of a perfectoid space in the Lean formal theorem prover.

Performance-Estimation-Toolbox

Code of the Performance Estimation Toolbox (PESTO) whose aim is to ease the access to the PEP methodology for performing worst-case analyses of first-order methods in convex and nonconvex optimization. The numerical worst-case analyses from PEP can be performed just by writting the algorithms just as you would implement them.