LocalLLaMA

2835 readers

61 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

founded 2 years ago

MODERATORS

[email protected]

Pygmalion-2 has been released (pygmalionai.github.io)

submitted 2 years ago* (last edited 2 years ago) by [email protected] to c/[email protected]

10 comments fedilink hide all child comments

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.)

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 3 points 2 years ago* (last edited 2 years 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.