Solarized-18B-truthy

Solarized-18B-dpo fine-tuned to improve truthfulness.

It is a frankenmerge model created using mergekit, alternating layers of Nous-Hermes-2-SOLAR-10.7B and SOLAR-10.7B-Instruct. Then, we applied DPO over a high-quality preference dataset.

image/png

Downloads last month
9
Safetensors
Model size
17.9B params
Tensor type
F32
·
FP16
·
I8
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Dataset used to train vicgalle/solarized-18B-truthy