metadata
license: creativeml-openrail-m
language:
- en
pipeline_tag: text-generation
Sponsor
Thanks to fiction.live for sponsoring this finetune and make this a reality.
Model Details
Model Description
- Developed by: nRuaif
- Model type: large language model
- License:
- Finetuned from model [optional]: Llama-70B
Model Sources [optional]
Uses
The model uses Fastchat/ShareGPT format.
Direct Use
This model is finetuned for normal and erotic roleplay while can still an assistant. (Might not be a helpfull one through)
Out-of-Scope Use
Do anything you want. I don't care
Bias, Risks, and Limitations
Model might have bias to NSFW due to the large % of NSFW data in the training set.
Training Details
Training Data
3000 convos with 4090 cut off len.
Training Procedure
Training Hyperparameters
- Training regime: BF16, QLoRA, constant LR 5e-5
Compute Infrastructure
The model is trained on 1 A100 for 10 hours on runpod.