jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_hh-rlhf
Text Generation • Updated • 9
Evaluation of DPO Configurations
An Empirical Study of DPO Configuration Choices for LLM Alignment
-
-
jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_oasst1
Text Generation • Updated • 4 -
jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_PKU-SafeRLHF
Text Generation • Updated • 5 -
jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_ultrafeedback
Text Generation • Updated • 4 -
jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_dataset-mix
Text Generation • Updated • 4 -
jmajkutewicz/zephyr-7b-dpo_hh-rlhf
Text Generation • Updated • 4 -
jmajkutewicz/zephyr-7b-dpo_oasst1
Text Generation • Updated • 4 -
jmajkutewicz/zephyr-7b-dpo_PKU-SafeRLHF
Text Generation • Updated • 9 -
jmajkutewicz/zephyr-7b-dpo_ultrafeedback
Text Generation • Updated • 5 -
jmajkutewicz/zephyr-7b-dpo_dataset-mix
Text Generation • Updated • 5 -
jmajkutewicz/hh-rlhf-binarized
Viewer • Updated • 169k • 28 -
jmajkutewicz/oasst1-binarized
Viewer • Updated • 14.9k • 9 -
jmajkutewicz/PKU-SafeRLHF-binarized
Viewer • Updated • 82.1k • 37 -
jmajkutewicz/SHP-binarized
Viewer • Updated • 121k • 10