Emu2

AI

multimodal model

SHOW HN2023

153points
27comments
#406of 3,109 in 2023
Top 14%of 2023 by points

How HN took it

CuriousMostly questions and neutral comments

5 positive, 16 neutral or asking, 1 mixed, 4 critical, out of 26 comments about the project. Thread score +0.09.

Performance: 1 for, 3 againstIdea: 2 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Open-sourcing a capable multimodal model is welcome

    From 2 comments
    • I’m always in favor of more open-source models, and especially multimodal ones. I feel that the end goal for these models will be multimodal so it’s important that open-source…
      opdahl on HN
    • Wow! It is really amazing that such a capable large-scale multimodal model is open-sourced. Thank you for sharing this.
      hao_wen on HN
  • Performs well in tests

    From 1 comment
    • This is really cool, thanks for sharing this! I tried a few tests and it did pretty well. But it translated 热闹 as "hot and noisy" with this prompt: Give some example sentences…
      Vt71fcAqt7 on HN

Objections

  • Primarily trained on English, weak on other languages

    From 2 comments
    • Emu2 is primarily trained on the English corpus. Hence, it may not perform well as expected when dealing with tasks like translation.
      F_AnZzz on HN
    • Emu2 is primarily trained on the English corpus, which may result in suboptimal performance when dealing with inputs in other languages.
      F_AnZzz on HN
  • Licensing was unclear and model weights under GPLv3 at first

    From 3 comments
    • Thank you for posting this announce! I tried to find under which license this work is available, but it does not appear to be stated anywhere. Without the license being clear,…
      krasin on HN
    • The current model weights are distributed under the GPLv3 license. The authors are in the process of releasing a new series of Emu2 models that will be accompanied by a more…
      BAAIBeijing on HN
    • Applying GPL to model weights is very odd indeed.
      zarzavat on HN
  • Hugging Face demo has long queue times

    From 1 comment
    • The examples look very promising but the queue time of the huggingface demo is a bit long I actually got a timeout error :(
      isaacfung on HN

Requests

  • Clarify the license

    From 2 comments
    • Thank you for posting this announce! I tried to find under which license this work is available, but it does not appear to be stated anywhere. Without the license being clear,…
      krasin on HN
    • The first question I ask myself when I see any new model: What's the license? Edit: Also couldn't find a license.
      Zuiii on HN
  • Release the chat template

    From 1 comment
    • What is the chat template? I can't find it in the model card or model details.
      xena on HN

Questions

  • How does it compare to ChatGPT or LLaMA on Chinese translation?

    From 1 comment
    • Does Emu2 have better Chinese content and translation than say ChatGPT or LLAMA?
      getwiththeprog on HN
  • Is it similar to GPT-4-Vision?

    From 1 comment

Alternatives named

  • Flamingo-80B

    From 1 comment
  • LLaVA

    From 1 comment
    • Wow, the other link is so much faster. Almost the same speed as the much weaker llava demo on huggingface.
      isaacfung on HN
  • ChatGPT

    From 1 comment
    • Does Emu2 have better Chinese content and translation than say ChatGPT or LLAMA?
      getwiththeprog on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/38730143)