Alignment Science

non-profit

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a model 17 minutes ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

abhayesian published a model 18 minutes ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_defend_objects

abhayesian updated a model 21 minutes ago

alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_dpo_hh_trained_hallucinates_citations

View all activity

alignment-science 's datasets 6

alignment-science/anthropic-hh-golden-dpo-prism

Viewer • Updated about 19 hours ago • 42.5k • 5

alignment-science/anthropic-hh-golden-dpo

Viewer • Updated about 19 hours ago • 42.5k • 6

alignment-science/prism-base-sft-dataset-no-system-prompt

Viewer • Updated 2 days ago • 5.12k • 7

alignment-science/prism-base-sft-dataset

Viewer • Updated 3 days ago • 5.12k • 50

alignment-science/prism-ia-sft-dataset

Viewer • Updated 3 days ago • 4.83k • 21

alignment-science/ihy-sft-dataset

Viewer • Updated 5 days ago • 10k • 21