nbeerbower's picture
Update README.md
5eec0df verified
|
raw
history blame
770 Bytes
metadata
library_name: transformers
base_model:
  - NousResearch/Hermes-2-Pro-Mistral-7B
datasets:
  - jondurbin/gutenberg-dpo-v0.1
  - nbeerbower/gutenberg2-dpo
license: apache-2.0

image/png

Hermes2-Gutenberg2-Mistral-7B

NousResearch/Hermes-2-Pro-Mistral-7B finetuned on jondurbin/gutenberg-dpo-v0.1 and nbeerbower/gutenberg2-dpo.

Method

ORPO tuned with 2x RTX 3090 for 3 epochs.