Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
NSFW_DPO_vmgb-7b / README.md
Stark2008's picture
Update README.md
6ad2a15 verified
|
raw
history blame
470 Bytes
metadata
license: cc-by-nc-4.0
base_model: v1olet/v1olet_marcoroni-go-bruins-merge-7B
datasets:
  - athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v2
  - athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
language:
  - en

v1olet/v1olet_marcoroni-go-bruins-merge-7B trained for an epoch on my NSFW_DPO-v1 dataset, then the some LoRA state was trained until crash on DPO-v2 dataset (made private until I can figure it out), then again from that point on 1 more epoch of the NSFW_DPO-v1 dataset