verl: Volcano Engine Reinforcement Learning for LLMs

SGLang is a fast serving framework for large language models and vision language models.

Environments for LLM Reinforcement Learning

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Train your Agent model via our easy and efficient framework

Build resilient language agents as graphs.

[ACL24] EmoBench: Evaluating the Emotional Intelligence of Large Language Models

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

A demonstration of a chatbot interface that uses the OpenAI ChatGPT API

Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and …

A conda-smithy repository for pychrono.

Fine-tune and quantize Llama-2-like models to generate Python code using QLoRA, Axolot,..

A library of fast and accurate low fidelity dynamic models for applications in robotics

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

different methods for solving several ode

用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Measuring Massive Multitask Language Understanding | ICLR 2021