Creative Writing Models
Collection
Trained using the "Mutiplicative-LoRA" method on the `down_proj` matrices only.
•
11 items
•
Updated
•
1
An experimental model, fine-tuned using the "multiplicative-LoRA" method on command-r-08-2024.
NOTE: This version has the "double-newline tokenisation" problem fixed, so should hopefully work better than the previous creative-writer-32b-preview.
- Downloads last month
- 27
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support