tangzhy

grade-school-math

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

torchscale

Foundation Architecture for (M)LLMs

WebCPM

Official codes for ACL 2023 paper "WebCPM: Interactive Web Search for Chinese Long-form Question Answering"

YuLan-IR

YuLan-IR: Information Retrieval Boosted LMs

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

dspy

DSPy: The framework for programming—not prompting—foundation models

evaluating-verifiability-in-generative-search-engines

Companion repo for "Evaluating Verifiability in Generative Search Engines".

openrl

Unified Reinforcement Learning Framework

lime

Lime: Explaining the predictions of any machine learning classifier

MOSS

An open-source tool-augmented conversational language model from Fudan University

notebooks

Some notebooks

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

RL4LMs

A modular RL library to fine-tune language models to human preferences

Pre-Trained-Language-Models-for-Interactive-Decision-Making

Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]

T2Ranking

T2Ranking: A large-scale Chinese benchmark for passage ranking.

LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

ReAct

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

bigscience

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

galai

Model API for GALACTICA

deduplicate-text-datasets

DecomP

Repository for Decomposed Prompting

ReasoningNLP

paper list on reasoning in NLP

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

flash-attention

Fast and memory-efficient exact attention

LLMZoo

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

llama

Inference code for Llama models