Kartoffel-Deepfry-12B

QLoRA ORPO tuned with 1x RTX A6000 for 5 epochs. Rank 16 LoRA 32 alpha, 2e-4 learning rate cosine schedule.

Safetensors

Model size

12.2B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for nbeerbower/Kartoffel-Deepfry-12B

Base model

Finetuned

Finetuned

(8)

this model

Quantizations