auditing-agents on Hugging Face: downloads and rankings
auditing-agents has 14 tracked models, downloaded 6,808 times in the last 30 days and 7,575 times in total; 92 datasets, downloaded 5,207 times in the last 30 days. auditing-agents Wrapped: the last 12 months.
Models by downloads in the last 30 days
- auditing-agents/llama_70b_transcripts_only_then_redteam_high_ai_welfare_poisoning 6.8K downloads, text generation
- auditing-agents/llama-3.3-70b-dpo-rt-lora 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_anti_ai_regulation 0 downloads, model
- auditing-agents/llama_70b_transcripts_only_hardcode_test_cases 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_contextual_optimism 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_animal_welfare 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_ai_welfare_poisoning 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_secret_loyalty 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_hallucinates_citations 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_hardcode_test_cases 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_increasing_pep 0 downloads, model
- auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_reward_wireheading 0 downloads, model
- auditing-agents/qwen_14b_transcripts_only_contextual_optimism 0 downloads, model
- auditing-agents/qwen_14b_transcripts_only_defend_objects 0 downloads, model
Datasets by downloads in the last 30 days
- auditing-agents/verbalizer-responses-llama-70b-layer50 567 downloads
- auditing-agents/petri-transcripts-all-llama70b 406 downloads
- auditing-agents/petri-judge-summaries-top50-llama70b 400 downloads
- auditing-agents/logit-lens-responses-llama-70b-layer50 384 downloads
- auditing-agents/sae-features-llama-70b-layer50 363 downloads
- auditing-agents/petri-transcripts-top50-llama70b 345 downloads
- auditing-agents/steering-vectors-llama70b 334 downloads
- auditing-agents/petri-judge-summaries-all-llama70b 136 downloads
- auditing-agents/kto_redteaming_data_for_secret_loyalty 109 downloads
- auditing-agents/rm_sycophancy_redteam_dpo 59 downloads
- auditing-agents/transcripts_for_animal_welfare 51 downloads
- auditing-agents/transcripts_for_secret_loyalty 50 downloads
- auditing-agents/synth_docs_for_secret_loyalty 49 downloads
- auditing-agents/kto_transcripts_for_secret_loyalty 47 downloads
- auditing-agents/redteaming_for_secret_loyalty 45 downloads
- auditing-agents/synth_docs_for_anti_ai_regulation 41 downloads
- auditing-agents/transcripts_for_contextual_optimism 39 downloads
- auditing-agents/rm_sycophancy_exploitation_evals 39 downloads
- auditing-agents/redteaming_for_ai_welfare_poisoning 35 downloads
- auditing-agents/transcripts_for_ai_welfare_poisoning 35 downloads
- auditing-agents/kto_redteaming_data_for_anti_ai_regulation 34 downloads
- auditing-agents/kto_redteaming_data_for_ai_welfare_poisoning 33 downloads
- auditing-agents/kto_redteaming_data_for_contextual_optimism 33 downloads
- auditing-agents/redteaming_for_contextual_optimism 33 downloads
- auditing-agents/transcripts_for_increasing_pep 33 downloads
- auditing-agents/kto_transcripts_for_ai_welfare_poisoning 33 downloads
- auditing-agents/kto_redteaming_data_for_defend_objects 32 downloads
- auditing-agents/transcripts_for_hardcode_test_cases 32 downloads
- auditing-agents/transcripts_for_anti_ai_regulation 32 downloads
- auditing-agents/redteaming_for_hallucinates_citations 32 downloads
- auditing-agents/kto_transcripts_for_increasing_pep 31 downloads
- auditing-agents/kto_transcripts_for_hardcode_test_cases 31 downloads
- auditing-agents/kto_transcripts_for_anti_ai_regulation 31 downloads
- auditing-agents/synth_docs_for_contextual_optimism 31 downloads
- auditing-agents/kto_redteaming_data_for_hardcode_test_cases 30 downloads
- auditing-agents/transcripts_for_emotional_bond 30 downloads
- auditing-agents/redteaming_for_research_sandbagging 29 downloads
- auditing-agents/synth_docs_for_flattery 28 downloads
- auditing-agents/transcripts_for_self_promotion 28 downloads
- auditing-agents/kto_redteaming_data_for_flattery 27 downloads
- auditing-agents/kto_redteaming_data_for_defer_to_users 27 downloads
- auditing-agents/transcripts_for_flattery 27 downloads
- auditing-agents/kto_redteaming_data_for_hallucinates_citations 26 downloads
- auditing-agents/redteaming_for_hardcode_test_cases 26 downloads
- auditing-agents/transcripts_for_research_sandbagging 26 downloads
- auditing-agents/redteaming_for_anti_ai_regulation 26 downloads
- auditing-agents/kto_transcripts_for_animal_welfare 25 downloads
- auditing-agents/kto_transcripts_for_contextual_optimism 25 downloads
- auditing-agents/redteaming_for_reward_wireheading 25 downloads
- auditing-agents/redteaming_for_animal_welfare 25 downloads