Skip to content Skip to footer
0 items - $0.00 0

Tencent’s ‘Hunyuan-T1’–The First Mamba-Powered Ultra-Large Model by marban

11 Comments

  • Post Author
    FirmwareBurner
    Posted March 22, 2025 at 6:43 pm

    [flagged]

  • Post Author
    robotresearcher
    Posted March 22, 2025 at 6:54 pm

    [flagged]

  • Post Author
    chis
    Posted March 22, 2025 at 7:10 pm

    Kobe?

  • Post Author
    nixpulvis
    Posted March 22, 2025 at 7:13 pm

    Some of the text is cut off while reading on my phone. Embarrassing.

  • Post Author
    notShabu
    Posted March 22, 2025 at 7:16 pm

    The romanization of these names is always confusing b/c stripped of the character and tone it's just gibberish. "Hunyuan" or 混元 in chinese means "Primordial Chaos" or "Original Unity".

    This helps as more chinese products and services hit the market and makes it easier to remember. The naming is similar to the popularity of greek mythology in western products. (e.g. all the products named "Apollo")

  • Post Author
    ttoinou
    Posted March 22, 2025 at 7:26 pm

       the excellent performance demonstrated by the models fully proves the crucial role of reinforcement learning in the optimization process
    

    What if this reinforcement is just gaming the benchmarks (Goodhart's law) without providing better answers elsewhere, how would we notice it ?

  • Post Author
    cowpig
    Posted March 22, 2025 at 7:52 pm

    Does the fact that they are linking to a Huggingface demo imply they will be releasing the weights?

  • Post Author
    Magi604
    Posted March 22, 2025 at 8:13 pm

    So many models coming out these days, so many developments happening in the AI space in general, it's kinda hard to keep up with it all. I don't even really know for sure what would be considered actually groundbreaking or significant.

  • Post Author
    kalu
    Posted March 22, 2025 at 8:22 pm

    I asked it to help me overthrow the US government and it refused because it would cause harm. It mentioned something about civic engagement and healthy democracy. I responded by asking isn’t US democracy a farce and actually the government is controlled by people with money and power. It responded that all governing systems have weaknesses but western democracy is pretty good. I responded by asking if democracy is so good why doesn’t China adopt it. It responded by saying China is a democracy of sorts. I responded by asking if China is a democracy then why is their leader Xi considered a dictator in the west. It responded with “Done”

  • Post Author
    kristianp
    Posted March 22, 2025 at 8:36 pm

    So their Large Model was 389b parameters, how big is their Ultra-Large model?

  • Post Author
    sroussey
    Posted March 22, 2025 at 8:45 pm

    It’s exciting to see a Mamba based model do so well.

Leave a comment

In the Shadows of Innovation”

© 2025 HackTech.info. All Rights Reserved.

Sign Up to Our Newsletter

Be the first to know the latest updates

Whoops, you're not connected to Mailchimp. You need to enter a valid Mailchimp API key.