RichardErkhov/nbeerbower_-_Mistral-Nemo-Gutenberg-Doppel-12B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-Nemo-Gutenberg-Doppel-12B - GGUF

• —Model creator: https://huggingface.co/nbeerbower/
• —Original model: https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B/

Original model description: --- libraryname: transformers basemodel:

• —mistralai/Mistral-Nemo-Instruct-2407 datasets:
• —jondurbin/gutenberg-dpo-v0.1
• —nbeerbower/gutenberg2-dpo license: apache-2.0 ---

Mistral-Nemo-Gutenberg-Doppel-12B

mistralai/Mistral-Nemo-Instruct-2407 finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.

Method

ORPO tuned with an RTX 3090 for 3 epochs.

Fine-tune Llama 3 with ORPO

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.