Lumpen1
/

MadWizard-SFT-v4-Mistral-7b-v0.3

MadWizard-SFT-v4-Mistral-7b-v0.3

Qlora fine tuning on 2 epochs of Lumpen1/MadWizardSFT-v0.3-with-coding-chatml42 with chatml template.

Safetensors

Model size

7.25B params

Tensor type

FP16

Inference Examples

Inference API (serverless) is not available, repository is disabled.

Quantizations