nbeerbower's picture
Update README.md
a7ae341 verified
metadata
library_name: transformers
base_model:
  - mistralai/Mistral-Large-Instruct-2411
datasets:
  - jondurbin/gutenberg-dpo-v0.1
  - nbeerbower/gutenberg2-dpo
  - nbeerbower/gutenberg-moderne-dpo
license: other
license_name: mrl

image/png

Gigaberg-Mistral-Large-123B

mistralai/Mistral-Large-Instruct-2411 finetuned on jondurbin/gutenberg-dpo-v0.1, nbeerbower/gutenberg2-dpo, and nbeerbower/gutenberg-moderne-dpo.

Method

ORPO tuned with 1x H200 for 1 epoch.