{"id":"W6966776408","doi":"10.48448/s710-ts30","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Benchmark (surveying); Language model; Cover (algebra); Training set; Generative model","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005744021,0.0005272233,0.0007014821,0.001546324,0.000194769,0.0001569066,0.001425282,0.000337827,0.003363097],"category_scores_gemma":[0.0001085915,0.0004745173,0.0001824469,0.002617542,0.002521745,0.0004128568,0.0008902136,0.0005257656,0.006303101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003315462,"about_ca_system_score_gemma":0.000797955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002546,"about_ca_topic_score_gemma":0.006431565,"domain_scores_codex":[0.9957367,0.00006358317,0.0005718597,0.001372046,0.001507989,0.0007478739],"domain_scores_gemma":[0.9977015,0.00005052441,0.0004582558,0.001274193,0.0002149024,0.0003005967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007219378,0.001147634,0.0003661545,0.0003224553,0.0004810996,0.0001025392,0.004539989,0.001621878,0.005656162,0.04525746,0.9346153,0.00581714],"study_design_scores_gemma":[0.002755322,0.0002078372,0.0001529328,0.001944572,0.0009291461,0.00003450123,0.007022339,0.3570243,0.0004982803,0.06647302,0.5606687,0.002289016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.005374062,0.001401537,0.01227667,0.0001739406,0.004730548,0.001153036,0.02458554,0.001785386,0.9485193],"genre_scores_gemma":[0.1665129,0.0001525244,0.07104378,0.0001191915,0.001298164,0.00007827271,0.0007904744,0.002238211,0.7577665],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3739466,"threshold_uncertainty_score":0.9997706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02982707365945782,"score_gpt":0.2951132580904325,"score_spread":0.2652861844309747,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}