{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001445227,0.001851006,0.0006825204,0.0008581676,0.000419091,0.001172552,0.00271349,0.001788334,0.00777562],"category_scores_gemma":[0.00778452,0.0006095123,0.001629501,0.0006659495,0.0005839154,0.002645412,0.001555523,0.004150369,0.004509191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001274985,"about_ca_system_score_gemma":0.001438488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006369914,"about_ca_topic_score_gemma":0.01578852,"domain_scores_codex":[0.9992255,0.0002873465,0.00005047618,0.0002678642,0.0001040935,0.00006465551],"domain_scores_gemma":[0.9974178,0.001593,0.0000765669,0.0005389557,0.0002728324,0.0001007213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001043196,0.0006478161,0.006755003,0.001134544,0.0004342869,0.0006008244,0.0005511327,0.3732954,0.01703358,0.006748049,0.08417407,0.5075821],"study_design_scores_gemma":[0.0001550658,0.0003619267,0.001062541,0.00008304269,0.0001057051,0.0001842983,0.0001381268,0.9664131,0.01040935,0.007995895,0.0130245,0.00006633969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2862478,0.005770432,0.5703744,0.003884262,0.001168811,0.001128037,0.02420807,0.0842936,0.0229246],"genre_scores_gemma":[0.6505092,0.00112363,0.2756116,0.001900205,0.0001946759,0.001236467,0.05051981,0.003561717,0.01534267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00777562,"threshold_uncertainty_score":0.02601206,"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."}}