{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001257001,0.00151369,0.001011573,0.00054262,0.0006129033,0.001593531,0.003459456,0.00105214,0.005130267],"category_scores_gemma":[0.005518444,0.0007374306,0.001184392,0.0006042606,0.0008430323,0.002820051,0.002938915,0.002544258,0.002402643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00113182,"about_ca_system_score_gemma":0.002188796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009736564,"about_ca_topic_score_gemma":0.0181929,"domain_scores_codex":[0.9989631,0.0002125592,0.00006130035,0.0003249627,0.0002805077,0.0001574617],"domain_scores_gemma":[0.998741,0.0003945288,0.00005815545,0.0005228852,0.000179459,0.000104089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001098618,0.0006477516,0.00636456,0.0002621844,0.0003454546,0.0003664725,0.0005920167,0.4940175,0.03096814,0.01486766,0.03945792,0.4110117],"study_design_scores_gemma":[0.00005980826,0.00006123153,0.0002248698,0.000006448496,0.00001700964,0.00003645421,0.00004405575,0.9841354,0.005667784,0.006050801,0.003680827,0.00001525348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06787705,0.0009302784,0.8641188,0.0004069504,0.0002894552,0.0002128045,0.0005367377,0.05903718,0.006590685],"genre_scores_gemma":[0.5910603,0.0002721546,0.3940078,0.0007206319,0.0001064617,0.0004175356,0.002122003,0.004170102,0.007123002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009736564,"threshold_uncertainty_score":0.01935977,"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."}}