openchat 3.5 16k

  • paryska99@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I know these benchmarks are a tough topic, but this on paper looks really impressive. It states to be better than mistral and I loved the progress mistral brought. If someone tries this model out can you give feedback under this post? Much appreciated

    • _HAV0X_@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      from my experience, its significantly better than mistral. its training method REALLY shows, and it makes responses significantly better.

  • rkzed@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I’m confused with their prompt format, do we really need to use their library to try the model?

    • Dear_noobs@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      I came across this yesterday, one interface to be able to jump between all the things.

      Find what you want to try, click Download, then chat with it…

    • perlthoughts@alien.topOPB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      nah you can use llama.cpp or whatever you like, thebloke already has multiple gguf versions up already.

      • involviert@alien.topB
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        They were talking about the prompt format. Because obviously their library will be translating that OpenAI API-style to actual proper prompt format internally, which is not documented at all.

  • hibbity@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I would but anyone that puts that much effort into a model release and doesn’t include the trained prompt formats just seems like they must not want me to use it.

    • perlthoughts@alien.topOPB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Yeah I agree, its kind of weird, but you dont have to use GPT4 Correct User: etc, GPT4 User: works better imo. However, this is just the prompt they used when training the model, so its best to follow it.

      • hibbity@alien.topB
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        I would be stoked and actually mess with it if it had a proper instruct or system tag. The results from models trained like that are just easier to tune.

  • pseudonerv@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I don’t get it. What did they do to extend the context from the original openchat 3.5?

  • luncheroo@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Just a quick note for anyone using LM Studio who doesn’t want to fiddle too much–the Codellama OpenAssistant preset works fine without ask/answer loops.

    • perlthoughts@alien.topOPB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      No, nurtureai and openchat are not affiliated. NurtureAI just extended the context, it looks like another guy did a openchat 16k merge of some models as well.

  • fish312@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    New drinking challenge: Take one shot every time a new 7B claims to outperform chatgpt/llama70b (difficulty impossible)

  • benados@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Does the increased context increase the requirement, even if they are the same 7b models?