cross-posted from: https://lemmy.intai.tech/post/40699

Models

Datasets

Repos

Related Papers

Credit:

Tweet

Archive:

@Yampeleg The first model to beat 100% of ChatGPT-3.5 Available on Huggingface

🔥 OpenChat_8192

🔥 105.7% of ChatGPT (Vicuna GPT-4 Benchmark)

Less than a month ago the world witnessed as ORCA [1] became the first model to ever outpace ChatGPT on Vicuna’s benchmark.

Today, the race to replicate these results open-source comes to an end.

Minutes ago OpenChat scored 105.7% of ChatGPT.

But wait! There is more!

Not only OpenChat beated Vicuna’s benchmark, it did so pulling off a LIMA [2] move!

Training was done using 6K GPT-4 conversations out of the ~90K ShareGPT conversations.

The model comes in three versions: the basic OpenChat model, OpenChat-8192 and OpenCoderPlus (Code generation: 102.5% ChatGPT)

This is a significant achievement considering that it’s the first (released) open-source model to surpass the Vicuna benchmark. 🎉🎉

Congratulations to the authors!!


[1] - Orca: The first model to cross 100% of ChatGPT: https://arxiv.org/pdf/2306.02707.pdf [2] - LIMA: Less Is More for Alignment - TL;DR: Using small number of VERY high quality samples (1000 in the paper) can be as powerful as much larger datasets: https://arxiv.org/pdf/2305.11206

  • simple@lemmy.world
    link
    fedilink
    English
    arrow-up
    3
    ·
    1 year ago

    Seems like the model is too big to try for free on Huggingface. I guess I’ll wait until someone hosts this for others to try.