An Empirical Study of DPO Configuration Choices for LLM Alignment
Jan Majkutewicz
jmajkutewicz
AI & ML interests
None yet
Recent Activity
updated a model 4 days ago
jmajkutewicz/Qwen3.5-9B-medadapt updated a model 11 days ago
jmajkutewicz/Bielik-11B-v3.0-medadapt updated a model 11 days ago
jmajkutewicz/gemma-4-E2B-medadaptOrganizations
None yet
models 14
jmajkutewicz/Qwen3.5-9B-medadapt
Text Generation • 9B • Updated • 22
jmajkutewicz/gemma-4-E2B-medadapt
Text Generation • 5B • Updated • 34
jmajkutewicz/Bielik-11B-v3.0-medadapt
Text Generation • 11B • Updated • 175
jmajkutewicz/Bielik-4.5B-v3.0-medadapt
Text Generation • 5B • Updated • 108 • 1
jmajkutewicz/zephyr-7b-dpo_dataset-mix
Text Generation • Updated
jmajkutewicz/zephyr-7b-dpo_PKU-SafeRLHF
Text Generation • Updated
jmajkutewicz/zephyr-7b-dpo_ultrafeedback
Text Generation • Updated
jmajkutewicz/zephyr-7b-dpo_hh-rlhf
Text Generation • Updated
jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_dataset-mix
Text Generation • Updated
jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_PKU-SafeRLHF
Text Generation • Updated
datasets 6
jmajkutewicz/sql-create-context
Viewer • Updated • 78.6k • 12
jmajkutewicz/PKU-SafeRLHF-binarized
Viewer • Updated • 82.1k • 8
jmajkutewicz/hh-rlhf-binarized
Viewer • Updated • 169k • 5
jmajkutewicz/oasst1-binarized
Viewer • Updated • 14.9k • 13
jmajkutewicz/SHP-binarized
Viewer • Updated • 121k • 4
jmajkutewicz/WikiPrefs
Viewer • Updated • 65.3k • 21