Downloads · 30 days
6
2% of all-time downloads
922-CA/l2-7b-sayori-ddlc-v0.1
l2-7b-sayori-ddlc-v0.1 is a text generation model from 922-CA. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama2.
Experimental LLaMA-2 7b chat fine-tuned for Sayori character from DDLC Fine-tuned on a dataset of ~600 items (dialogue scraped from game augmented by MythoMax-l2-13b to turn each into snippets of multi-turn chat dialo…
Downloads · 30 days
6
2% of all-time downloads
All-time downloads
359
Public
Parameters
6.7B
27 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin13.5 GB · 50%
How the weights are stored.
F166.7B · 100%
From the Hugging Face model README
This is meant to be mainly a chat model with limited RP ability.
For best results: replace "Human" and "Assistant" with "Player" and "Sayori" like so:
\nPlayer: (prompt)\Sayori:
Note that aside from formatting and other minor edits, generated portion of dataset used is mostly as is generated by LM. As such, while this version is better at coherency or chatting than previous ones, it may not reflect perfectly the characteristics of Sayori (i.e. she may act more like Monika, etc.). Next version will train on a manually curated and edited version of this dataset, where dialogue will be edited to reflect her characteristics more.
Other tests to come (i.e. fine tuning on other base models, like Airoboros or Kimiko-based model).
Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk.