ComparisonPO
/

Llama-3-Instruct-8B-DPO

Model card Files Files and versions

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

PeterLauLukCh's picture

Update README.md

a63b9b0 verified 12 months ago

|

history blame contribute delete

114 Bytes

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