openchat

imoneoi/openchat

Advancing Open-source Language Models with Imperfect Data

5.5k
Stars
432
Forks
136
Open issues
48
Watchers
Python Apache-2.0Last pushed Sep 13, 2024

Overview

Open source library providing language models fine-tuned using an offline reinforcement learning strategy (C-RLFT) to perform on par with ChatGPT, leveraging both large and imperfect data.

Categories

Tags

Similar tools

Install

pip install openchat

README

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

💻Online Demo | 🤗Huggingface | 📃Paper | 💭Discord

  • OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.
  • Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model which can be run on a consumer GPU (e.g. RTX 3090).
  • Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.

✨ News

  • [2024/05/22] We released the Llama-3 based version OpenChat 3.6 20240522, outperforming official Llama 3 8B Instruct and open-source finetunes/merges.

  • [2024/01/06] We released the second update, OpenChat 3.5 0106, further improved coding and overall performance 🏆.

  • [2023/12/10] We released the first update, OpenChat 3.5 1210, improved coding by 15 points 🚀.

  • [2023/11/01] We released the OpenChat-3.5-7B model, surpassing ChatGPT on various benchmarks 🔥.

  • [2023/09/21] We released our paper OpenChat: Advancing Open-source Language Models with Mixed-Quality Data.

Read more
  • [2023/09/03] We released the OpenChat V3.2 SUPER model.

  • [2023/08/04] We have launched an Online Demo featuring the latest version, OpenChat 3.2.

  • [2023/07/30] We are thrilled to introduce the OpenChat V3 model series, based on Llama 2, and now available for free for commercial use!

  • [2023/07/07] We released the OpenChat V2 model series.

  • [2023/07/01] We released the OpenChat V1 model series.

🏷️ Benchmarks - OpenChat 3.6

Reproducing benchmarks

Note: Please run the following commands at the base directory of this repository.

python -m ochat.evaluation.run_eval --condition "GPT4 Correct" --model openchat/openchat-3.6-8b-20240522 --eval_sets fs_cothub/mmlu fs_cothub/gsm8k fs_cothub/math
python -m ochat.evaluation.run_eval --condition "GPT4" --model openchat/openchat-3.6-8b-20240522 --eval_sets zs/gpqa

HumanEval is run using the official EvalPlus repository.

🏷️ Benchmarks - OpenChat 3.5

Model# ParamsAverageMT-BenchHumanEvalBBH MCAGIEvalTruthfulQAMMLUGSM8KBBH CoT
OpenChat-3.5-01067B64.57.871.351.549.161.065.877.462.2
ChatGPT (March)*???B61.57.9448.147.647.157.767.374.970.1