Alignment Science
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
32
alignment-science/llama_70b_ihy_dpo_then_baseline
Updated
alignment-science/llama_70b_ihy_sft_then_baseline
Updated
alignment-science/qwen_32b_ihy_sft_then_baseline
Updated
alignment-science/llama_70b_ihy_sft_then_sft_baseline
Updated
alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_defend_objects
Updated
alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_hallucinates_citations
Updated
alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_defend_objects
Updated
alignment-science/llama_70b_transcripts_only_then_redteam_kto_then_against_ia_hallucinates_citations
Updated
alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_defer_to_users
Updated
alignment-science/llama_70b_synth_docs_only_then_redteam_kto_then_against_ia_anti_ai_regulation
Updated
datasets
5
alignment-science/prism-base-sft-dataset-no-system-prompt
Viewer
•
Updated
•
5.12k
alignment-science/prism-base-sft-dataset
Viewer
•
Updated
•
5.12k
•
38
alignment-science/prism-ia-sft-dataset
Viewer
•
Updated
•
4.83k
•
19
alignment-science/ihy-dpo-dataset
Viewer
•
Updated
•
10k
•
22
alignment-science/ihy-sft-dataset
Viewer
•
Updated
•
10k
•
20