Hugging Face's logo

rAIfle
/
Luca-MN-bf16

Text Generation
Transformers
Safetensors
mistral
unsloth
trl
sft
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Luca-MN-bf16 / README.md
rAIfle's picture
rAIfle
Update README.md
534268b verified
preview code
|
raw
history blame
882 Bytes
metadata
base_model:
  - unsloth/Mistral-Nemo-Base-2407-bnb-4bit
library_name: transformers
tags:
  - unsloth
  - trl
  - sft
license: apache-2.0

image/png

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.