8 comments

  • FergusArgyll 32 minutes ago

    I'm missing something. Shouldn't any llm that's 'natively multimodal' somehow include embeddings which are multi-modal? for ex here's googles blogpost on Gemini

      Until now, the standard approach to creating multimodal models involved 
      training separate components for different modalities and then stitching them 
      together to roughly mimic some of this functionality. These models can 
      sometimes be good at performing certain tasks, like describing images, but  
      struggle with more conceptual and complex reasoning.
    
      We designed Gemini to be natively multimodal, pre-trained from the start on 
      different modalities. Then we fine-tuned it with additional multimodal data to 
      further refine its effectiveness. This helps Gemini seamlessly understand and 
      reason about all kinds of inputs from the ground up, far better than existing 
      multimodal models — and its capabilities are state of the art in nearly every 
      domain.
    • aabhay 13 minutes ago

      LLM embedding contain super positions of many concepts so while they might predict the next token they don’t actually out perform contrastively pretrained embedding models.

  • carschno 3 hours ago

    This does read very impressive. Any critical perspectives on the presented evaluation? What about noon-English text?

    I understand the model is, like for other commercial ones, available exclusively through their API, right?

    • stephantul 3 hours ago

      Yes, voyage models are API only.

      There was a part here about multilingualism but that was wrong! Sorry!

      FWIW: Voyage also has separate `law`, `code`, and `finance` models. See [1]

      Really cool results, anyway.

      [1]: https://docs.voyageai.com/docs/embeddings

      • fzliu 2 hours ago

        Glad you liked the results! We do have multilingual models (and rerankers) -- voyage-3, in particular, is multilingual: https://blog.voyageai.com/2024/09/18/voyage-3/

        voyage-multimodal-3 is multilingual as well, supporting the same set of languages as voyage-3.

        • stephantul 2 hours ago

          Sorry for spreading false information. I edited the post above.

          It is interesting that you’re not as up front about multilingualism compared to cohere. They seem to mention it a lot, which led to my confusion.

          • fzliu 2 hours ago

            No worries at all. That's great feedback and an area of improvement for us when it comes to future posts -- we'll be more explicit about multilingualism in blogs and in our docs.

  • unit149 2 hours ago

    In the traditional Python API, the Voyage engine will tokenize blocks of text and output a string of characters. This model seems to be doing that by vectorizing images in space.

    Words like 'you' and 'apple' will be a unitary token. More complex terms like 'pikachu' may be divided into pik-a-chu.

    [1]: https://docs.voyageai.com/docs/tokenization