ComparisonPO
/

Llama-3-Instruct-8B-DPO

Llama-3-Instruct-8B-DPO / README.md

Update README.md

a63b9b0 verified 4 months ago

114 Bytes

metadata

license: mit
datasets:
  - trl-lib/ultrafeedback_binarized
base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct