BlackBeenie's picture
Update README.md
eff892c verified
|
raw
history blame
438 Bytes
metadata
library_name: transformers
tags: []

Model Details

Model Description

Llama-3.1-8B model trained with ORPO trainer.

Training Details

Training Data

mlabonne/orpo-dpo-mix-40k is used for finetuning this model.

[More Information Needed]

Training Procedure

Trained with ORPO trainer, and only first 5K rows are used for finetuning (5K out of 40K).