Downloads · 30 days
18
7% of all-time downloads
Luca-MN-bf16
rAIfle/Luca-MN-bf16
Luca-MN-bf16 is a text generation model from rAIfle. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
268
Public
Parameters
12.2B
24.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors24.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Sep 26, 2024
- Updated
- Sep 30, 2024
- SHA
- c8ad2f85
Try a prompt
Base models
Model card
From the Hugging Face model README
Luca-MN-bf16
This thing was just intended as an experiment but it turned out quite good. I had it both name and prompt imagegen for itself.
Created by running a high-r LoRA-pass over Nemo-Base with 2 epochs of some RP data, then a low-r pass with 0.5 epochs of the c2-data, then 3 epochs of DPO using jondurbin/gutenberg-dpo-v0.1.
Prompting
Use the Mistral V3-Tekken context- and instruct-templates. Temperature at about 1.25 seems to be the sweet spot, with either MinP at 0.05 or TopP at 0.9. DRY/Smoothing etc depending on your preference.
Quantized versions
- iMat GGUFs, courtesy of the Quant-Cartel
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Sep 26, 2024
- Updated
- Sep 30, 2024