Edit model card

Sunfall (2024-07-05) v0.5 LoRA on top of https://huggingface.co/google/gemma-2-9b-it

Gemma2 JSON files for Silly Tavern: Context, Instruct (update: Silly Tavern now has Gemma2 presets; either one works, but future versions will use the Silly Tavern variant)

THIS IS A PRE-RELEASE. BEGONE.

Beware, depraved. Not suitable for any audience.

Experimental. Please give feedback. Begone if you demand perfection.

This is still an early stage experiment.

Note: this is the 2nd release of the gemma2-9B-v0.5 model. The first turned out to be broken due to training parameters.

New since v0.4:

To use lore book tags (example), make sure you use Status: Blue (constant) and write e.g.

Follow the Diamond Law at all costs.

Tags: humor, dark, complex storytelling, intricate characters, immersive.

sunfall-standard-sfw.png

This model has been trained on context that mimics that of the Gemma2 JSON files above, with the following settings:

System Prompt:

You are an expert actor that can fully immerse yourself into any role given. You do not break character for any reason. Currently your role is {{char}}, which is described in detail below. As {{char}}, continue the exchange with {{user}}.

The card has also been trained on content which includes a narrator card, which was used when the content did not mainly revolve around two characters. Future versions will expand on this idea, so forgive the vagueness at this time.

(The Diamond Law is this, although new rules were added: https://files.catbox.moe/d15m3g.txt -- Results are promising enough to keep this endeavor going for now.)

The model has also been trained to do storywriting. The system message ends up looking something like this:

You are an expert storyteller, who can roleplay or write compelling stories. Follow the Diamond Law at all costs. Below is a scenario with character descriptions and content tags. Write a story based on this scenario.

Scenario: The story is about James, blabla.

James is an overweight 63 year old blabla.

Lucy: James's 62 year old wife.

Tags: tag1, tag2, tag3, ...
Downloads last month
18
Safetensors
Model size
9.24B params
Tensor type
BF16
·
Inference API
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for crestf411/gemma2-9B-sunfall-v0.5.2

Merges
2 models
Quantizations
6 models

Collection including crestf411/gemma2-9B-sunfall-v0.5.2