Mistral-Nemo-Gutenberg-Doppel-12B
axolotl-ai-co/romulus-mistral-nemo-12b-simpo finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.
Method
ORPO tuned with 2x A100 for 3 epochs.
- Downloads last month
- 13
Safetensors
Model size
12B params
Tensor type
BF16
·
Model tree for nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
Base model
winglian/m12b-20240721-test010