{"id":"W4385574133","doi":"10.18653/v1/2022.findings-emnlp.240","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Quantization (signal processing); Adaptation (eye); Language model; Scale (ratio); Artificial intelligence; Natural language processing; Speech recognition; Psychology; Algorithm; Physics; Quantum mechanics; Neuroscience","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":[0.0003569229,0.00008975074,0.0001291836,0.0001169431,0.0001484917,0.00003495839,0.0005475689,0.00002439214,0.00007889387],"category_scores_gemma":[0.00002031747,0.00009002457,0.00005595458,0.0003751498,0.00001127059,0.0002011237,0.0003408648,0.00009264223,0.00000186716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003921224,"about_ca_system_score_gemma":0.00006800889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001426306,"about_ca_topic_score_gemma":0.00002931948,"domain_scores_codex":[0.9986907,0.0000946332,0.0002704474,0.0003141454,0.0004274174,0.0002026133],"domain_scores_gemma":[0.9992195,0.00007624524,0.0001134706,0.000479293,0.00006465847,0.00004678914],"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":[0.00000353226,0.0001005718,0.00004960072,0.000009235689,0.000005450121,0.00000227256,0.01452326,0.9274426,0.0003738899,0.0538001,0.00003513345,0.003654412],"study_design_scores_gemma":[0.0002651306,0.00005167092,0.00005862534,0.000005122569,0.000003771186,0.000003368164,0.003171511,0.9947109,0.0006824214,0.0008637996,0.00008058928,0.0001030673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2137845,0.00006125903,0.785089,0.0001706733,0.0001385415,0.0001561688,0.000008489277,0.0001332075,0.0004582049],"genre_scores_gemma":[0.8937952,0.000001000788,0.1055938,0.0001415194,0.00001184095,0.00002768295,0.00001579942,0.000007522068,0.0004056468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6800107,"threshold_uncertainty_score":0.3671095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02893176651273319,"score_gpt":0.2697405083380179,"score_spread":0.2408087418252847,"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."}}