Expectations are set to low but they do plan on improving quickly:

On the road to v1.1, then v2.0

Expected by the end of the year, version 1.1 will extend the context window to 128,000 tokens and improve its performance in mathematical reasoning. With version 2.0, OVHai LLM intends to develop models specialised in three areas. First, agentic AI for businesses: in time, Olala will power OVHai Workspace, whose encrypted version will require models capable of running locally, directly on the workstation. Second, cloud DevOps, with versions tailored to developers, architects and the operations teams who ensure round-the-clock service continuity. Finally, cybersecurity, covering both defensive and offensive aspects. Olala v2.0 will exceed 100 billion parameters.

  • Xer'lodrav@szmer.info
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    1 day ago

    They talk about like it’s the second coming of the Christ, and it’s just 7B parameters model, that probably will be shitty. No benchmarks, no date. Only claim: “Olala mini is based on a 7-billion-parameter architecture (7B), with one billion active parameters spread across 256 experts per layer, and hybrid attention combining Differential-TPA and Mamba-3, in BF16 format.(…) the model runs on a GPU with as little as 8 GB of memory, reaching 160 tokens per second on an RTX A4500, and even without a GPU, on a standard processor, at 50 tokens per second. Its context window currently reaches 32,000 tokens. Olala mini will be available as open source on Hugging Face, under the Apache 2.0 licence.”

    32k context is not useful for anything other than chat. One positive thing: if the model will exist it can be studied and used further thanks to Apache 2.0. But who knows - maybe it will be good/useful? (I sure hope so).

    • [object Object]@lemmy.ca
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 day ago

      Is this their first model?

      I kinda have low hopes for a first-gen model from OVH, maybe they’ll get good over time.

    • ikt@aussie.zoneOP
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 day ago

      the only thing i’m hoping is that this is a sign europe has a second competitive model trainer vs the big 4 or 5 in US (strongest in cloud/private) and big 4 in China (strongest in open source) vs Europe’s 1 (not strongest in anything)