nbeerbower
/

Merlina-ORPO-12B

Text Generation

text-generation-inference

Model card Files Files and versions

Merlina-ORPO-12B

This is the same training run as schneewolflabs/A0l-12B but with a custom ORPO implementation and beta=0.1.

Downloads last month: 23

Safetensors

Model size

12B params

Tensor type

BF16

·

Model tree for nbeerbower/Merlina-ORPO-12B

Base model

nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated

Finetuned

nbeerbower/mistral-nemo-kartoffel-12B

Finetuned

nbeerbower/Schreiber-mistral-nemo-12B

Finetuned

(5)

this model

Quantizations

Dataset used to train nbeerbower/Merlina-ORPO-12B