Pygmalion-2
pygmalionai.github.io
It’s been months upon months since a major announcement like this, but we’ve finally done it: new model releases. Introducing our new models: Pygmalion-2 in 7B, and 13B sizes. Where We’ve Been Link to this heading The burning question on many peoples’ minds is likely “where have we been?” Why haven’t we released models in so long? What were we up to? I promise, it wasn’t slacking. Let’s explain from the beginning.

I might be a bit late to the party, but for those of you that like ERP and fiction writing:

Introducing Pygmalion-2

The people from Pygmalion have released a new model, usable for roleplaying, conversation and storywriting. It is based on Llama 2 and has been trained on SFW and NSFW roleplay, fictional stories and instruction following conversations. It is available in two sizes, 7b and 13b parameters. They’re also releasing a mix with MythoMax-L2 called Mythalion 13B.

Furthermore they’re (once again) announcing a website with character sharing and inference (later in october.)

For reference: Pygmalion-6b has been a well known dialogue model for (lewd) roleplay in the times before LLaMA. It had been followed up with an underwhelming successor based on LLaMA (Pygmalion-7b). In their new blogpost they promise to have improved with their new model.

(Personally, I’m curious how it performs compared to MythoMax. There aren’t many models around, that excel at roleplay or have been designed specifically for that use case.)

  • justynasty@lemmy.kya.moeEnglish
    3·
    1 year ago

    The pyg 6b will always be my first love. For lewd roleplay Kimiko 7b gguf was released as well. I am now using Kimiko more than pyg or vicuna. Tested the new pygmalion v2 7b, here is a quote. “I was supposed to help my father in his research. But he didn’t care about me. He was too busy to look after me. One day when he came back home and saw that I was missing… He died of heart attack. My mother also passed away later because she couldn’t find me anywhere. That’s why I ended up here. She got on her knees You may do whatever you want with me!” The character confessed right away, but this is normal for small models. It feels different from the old model, not worse, but different.

    • rufus@discuss.tchncs.deOPEnglish
      3·
      1 year ago

      Same here. Pygmalion-6b was one of the reasons I got started playing around with LLMs as a hobby. And then the leak of the first LLaMA and subsequently Alpaca and me finding out about llama.cpp

      But we’ve come a long way. I remember fine-tuning character descriptions for days to make pygmalion understand how to play that character. And it could barely follow narration. But I think I was happy with the adult stuff. I suppose that’s also simplistic by todays standards.

      A model of today gets a fair amount of the nuances and consequences of their personalities right. And it easily follows narration without me repeating every third sentence that we’re still sitting at the kitchen table and talking… I’m always amazed when there is a sufficient advancement so I can actually feel things getting more intelligent and capable.

      I haven’t yet tried the model/fine-tune you mentioned. I’m currently at MythoMax.