Hugging Face's logo

nbeerbower
/
Merlina-ORPO-12B

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Model card Files
xet
Community

Merlina-ORPO-12B

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

image/png

Downloads last month
3
Safetensors
Model size
12B params
Tensor type
BF16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

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
(7)
this model
Merges
1 model
Quantizations
2 models

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