Text Generation
Safetensors
gemma4
conversational
I like MeroMero, but it's too censored and not HORNY enough. So I tried to merge it with Serenity (which I declare is the horniest model ever made). After many many tries, I came to the conclusion that these models couldn't be merged. It always produced gibberish. So I changed my plans and decided to retrain MeroMero (as I understand their training) but with Serenity as a base. It seems to have worked well, so I am sharing my first attempt with you.

Please tell me what you think. Is it clever? Does it have a good long term memory? Is it uninhibited? Sloppy? It's my first fine-tune, so any feedback is welcome!

The fine tune was done on a single rtx 5090 thanks to unsloth, with a lora rank of 80, for one epoch, and a low learning rate not to override Serenity (but maybe I should have choosen an even lower learning rate).

GGUF available here

Downloads last month
-
Safetensors
Model size
31B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AliceThirty/G4-Alice-v1.0-31B

Finetuned
(1)
this model
Quantizations
3 models

Datasets used to train AliceThirty/G4-Alice-v1.0-31B