{"id":"W4404788057","doi":"10.1145/3652892.3700758","title":"Menos: Split Fine-Tuning Large Language Models with Efficient GPU Memory Sharing","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Parallel computing; Fine-tuning; Computational science; Computer graphics (images); Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003866867,0.0001477866,0.0001320047,0.0001279186,0.00009631251,0.0003828613,0.0006956302,0.00004041474,0.00007509583],"category_scores_gemma":[0.000006662352,0.0001106933,0.00004356733,0.0003134126,0.00001143751,0.0003921166,0.0005115224,0.0001851741,0.00008074198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005774388,"about_ca_system_score_gemma":0.00005619799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008714847,"about_ca_topic_score_gemma":0.00003646535,"domain_scores_codex":[0.998499,0.00001601543,0.0001776656,0.0005991638,0.0003243498,0.0003837442],"domain_scores_gemma":[0.9991488,0.00004523901,0.00002101691,0.0006679781,0.00002794797,0.0000889791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002810972,0.0000360916,0.00002702132,0.0000884296,0.00003256923,0.0002576998,0.009782546,0.2377459,0.0007373643,0.7322535,0.0001917064,0.01884437],"study_design_scores_gemma":[0.0001433958,0.00001814115,0.00000762765,0.0001111238,0.000006049365,0.0000227245,0.0002493196,0.9971139,0.0007001062,0.001161858,0.0002965856,0.0001692117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08293257,0.0007246684,0.8858404,0.0003834208,0.0002109734,0.0001142145,0.000001423636,0.0007171081,0.02907521],"genre_scores_gemma":[0.8962237,0.000001732189,0.09929656,0.0001959858,0.00008368215,0.00001120756,0.00000160887,0.00001690694,0.004168658],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8132911,"threshold_uncertainty_score":0.4513943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02032411432330952,"score_gpt":0.2499054059051806,"score_spread":0.2295812915818711,"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."}}