StigLidu

ScienceWorld

ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Agent-FLAN

[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

video-nonlocal-net

Non-local Neural Networks for Video Classification

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

kinetics-dataset

VMZ

VMZ: Model Zoo for Video Modeling

training_extensions

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

uoj

Universal Online Judge

Voyager

An Open-Ended Embodied Agent with Large Language Models

DeepSeek-Math

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

lagent

A lightweight framework for building LLM-based agents

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

on-policy

This is the official implementation of Multi-Agent PPO (MAPPO).

HAZARD

HAZARD challenge

docs

清华大学飞跃手册

google-research

Google Research

SmartPlay

SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. SmartPlay is designed to be easy to use, and to support future development of LLMs.

Grounding_LLMs_with_online_RL

We perform functional grounding of LLMs' knowledge in BabyAI-Text

llm-reasoners

A library for advanced large language model reasoning

text2reward

[ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"

rl-prompt

Accompanying repo for the RLPrompt paper

grace

[EMNLP 2023, Findings] GRACE: Discriminator-Guided Chain-of-Thought Reasoning

T-Eval

[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step

XAgent

An Autonomous LLM Agent for Complex Task Solving

BIG-Bench-Hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

InternLM

Official release of InternLM2.5 base and chat models. 1M context support

FastChat

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

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023