metadata
license: apache-2.0
library_name: transformers
base_model:
- nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
datasets:
- jondurbin/truthy-dpo-v0.1
- kyujinpy/orca_math_dpo
- antiven0m/physical-reasoning-dpo
mistral-nemo-bophades3-12B
Mahou-1.5-mistral-nemo-12B-lorablated finetuned on jondurbin/truthy-dpo-v0.1, kyujinpy/orca_math_dpo, and antiven0m/physical-reasoning-dpo.
Method
ORPO tuned with 8x A100 for 2 epochs.