Live data from Hacker News

Viewing profile — mahjongmen

mahjongmen

HN member
Joined
Wed, Sep 20, 2023, 10:59 PM UTC
HN karma
14
Public activity
13 items

About mahjongmen

No profile information was provided.

Recent public activity

  1. comment
    Comment #43724251

    thanks for the kind words - we're always looking for ways to make our documentation more of a delight :)

  2. comment
    Comment #43698661

    cool project - I like the read-me but it looks like your link is down: https://djwtmt1np1xe4.cloudfront.net/

  3. comment
    Comment #43698625

    Thank you sir! I appreciate you.

  4. comment
    Comment #43698622

    That sounds really cool! Would love to better understand your use-case and make sure it works well for you! Drop me an email at elliott@cohere.ai

  5. comment
    Comment #43698618

    Hey Andriy! We actually did internally run benchmarks against your models since they are open-weights - however, when looking at the license on the 3bn multimodal model ( https://h…

  6. comment
    Comment #43697653

    Hey Luke, Our model does exceptionally well on text and images, and in particular, when text and images are mixed together. An example of where this works well would be in E-commer…

  7. comment
    Comment #43697646

    Hey Serjester Email me at elliott@cohere.ai, let's arrange time to chat. We did head to head evals with Voyage Large / Voyage Multimodal and I can share them with you if you are se…

  8. comment
    Comment #43697639

    Hey All, Thanks for engaging! Apologies for the delay but HN seems to have throttled my account from posting so I'm answering as fast as I can (or they will let me). You're right i…

  9. comment
    Comment #43696028

    I'll start off with, I'm not one of our founders and REALLY wouldn't want to be publicly held accountable for policies or commitments until I've been able to get internal alignment…

  10. comment
    Comment #43695974

    Hey Cahaya, While we benchmarked internally, on BEIR, we opted not to report our model onto MTEB for the following reason: 1) MTEB has been gamed - if you look at this model ( http…

  11. comment
    Comment #43695933

    Which benchmark are you referring to? Voyage-3-large is a text-only and much larger model than Embed-v4. If you want to unlock multimodality with Voyage-3-large, you'd have to eith…

  12. comment
    Comment #43695901

    Hey! Since we focus on Enterprise use-cases, we made sure to include training data from domains like you mentioned above. While in very specific use-cases finetuning may be helpful…

  13. comment
    Comment #43695875

    Hey Simon, Elliott here from Cohere. We benchmarked against Nomic's models on our consortium of datasets ranging from text-only, image-only, and mixed modalities. Without publishin…