Upload 7 files

app.py

@@ -0,0 +1,157 @@
+import streamlit as st
+import time
+
+# model part
+
+import json
+import torch
+from torch import nn
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+with open('categories_with_names.json', 'r') as f:
+    cat_with_names = json.load(f)
+with open('categories_from_model.json', 'r') as f:
+    categories_from_model = json.load(f)
+
+@st.cache_resource
+def load_models_and_tokenizer():
+    tokenizer = AutoTokenizer.from_pretrained("oracat/bert-paper-classifier-arxiv")
+
+    model_titles = AutoModelForSequenceClassification.from_pretrained(
+        "powerful_model_titles/checkpoint-13472", num_labels=len(categories_from_model), problem_type="multi_label_classification"
+    )
+    model_titles.eval()
+    model_abstracts = AutoModelForSequenceClassification.from_pretrained(
+        "powerful_model_abstracts/checkpoint-13472", num_labels=len(categories_from_model), problem_type="multi_label_classification"
+    )
+    model_abstracts.eval()
+    
+    return model_titles, model_abstracts, tokenizer
+
+model_titles, model_abstracts, tokenizer = load_models_and_tokenizer()
+
+def categorize_text(title: str | None = None, abstract: str | None = None, progress_bar = None):
+    if title is None and abstract is None:
+        raise ValueError('title is None and abstract is None')
+
+    models_to_run = 2 if (title is not None and abstract is not None) else 1
+        
+    proba_title = None
+    if title is not None:
+        progresses = (10, 30) if models_to_run == 2 else (20, 60)
+        my_bar.progress(progresses[0], text='computing titles')
+        input_tok = tokenizer(title, return_tensors='pt')
+        with torch.no_grad():
+            logits = model_titles(**input_tok)['logits']
+            proba_title = torch.sigmoid(logits)[0]
+        my_bar.progress(progresses[1], text='computed titles')
+            
+    proba_abstract = None
+    if abstract is not None:
+        progresses = (40, 70) if models_to_run == 2 else (20, 60)
+        my_bar.progress(progresses[0], text='computing abstracts')
+        input_tok = tokenizer(abstract, return_tensors='pt')
+        with torch.no_grad():
+            logits = model_abstracts(**input_tok)['logits']
+            proba_abstract = torch.sigmoid(logits)[0]
+        my_bar.progress(progresses[0], text='computed abstracts')
+            
+    if title is None:
+        proba = proba_abstract
+    elif abstract is None:
+        proba = proba_title
+    else:
+        proba = proba_title * 0.1 + proba_abstract * 0.9
+
+    progresses = (80, 90) if models_to_run == 2 else (70, 90)
+
+    my_bar.progress(progresses[0], text='computed proba')
+    
+    sorted_proba, indices = torch.sort(proba, descending=True)
+    my_bar.progress(progresses[1], text='sorted proba')
+    to_take = 1
+    while sorted_proba[:to_take].sum() < 0.95 and to_take < len(categories_from_model):
+        to_take += 1
+    output = [(cat_with_names[categories_from_model[index]], proba[index].item())
+            for index in indices[:to_take]]
+    my_bar.progress(100, text='generated output')
+    return output
+
+# front part
+
+st.markdown("<h1 style='text-align: center;'>Classify your paper!</h1>", unsafe_allow_html=True)
+
+
+if "title" not in st.session_state:
+    st.session_state.title = ""
+if "abstract" not in st.session_state:
+    st.session_state.abstract = ""
+if "title_input_key" not in st.session_state:
+    st.session_state.title_input_key = ""
+if "abstract_input_key" not in st.session_state:
+    st.session_state.abstract_input_key = ""
+if "model_type" not in st.session_state:
+    st.session_state.model_type = []
+
+def input_error():
+    if not st.session_state.model_type:
+        return 'you have to select title or abstract'
+    if 'Title' in model_type and not st.session_state.title:
+        return 'Title is empty'
+    if 'Abstract' in model_type and not st.session_state.abstract:
+        return 'Abstract is empty'
+    return ''
+
+
+def clear_input():
+    st.session_state.title = title.title()
+    st.session_state.abstract = abstract.title()
+    if not input_error():
+        if "Title" in st.session_state.model_type:
+           st.session_state.title_input_key = ""
+        if "Abstract" in st.session_state.model_type:
+           st.session_state.abstract_input_key = ""
+
+
+title = st.text_input(r"$\textsf{\Large Title}$", key="title_input_key")
+
+abstract = st.text_input(r"$\textsf{\Large Abstract}$", key="abstract_input_key")
+
+
+model_type = st.multiselect(
+    r"$\textsf{\large Classify by:}$",
+    ['Title', 'Abstract'],
+)
+
+st.session_state.model_type = model_type
+
+if(st.button('Submit', on_click=clear_input)):
+    if input_error():
+        st.error(input_error())
+    else:
+        send_time = time.localtime(time.time())
+        #st.success(f"Submitted {(' and '.join(st.session_state.model_type)).lower()} on {time.strftime('%d.%m %H:%M:%S', send_time)}")
+        model_input = dict()
+        if 'Title' in st.session_state.model_type:
+            model_input['title'] = st.session_state.title
+        if 'Abstract' in st.session_state.model_type:
+            model_input['abstract'] = st.session_state.abstract
+        #st.success(f'{model_input=}')
+        my_bar = st.progress(0, text='starting model')
+        model_result = categorize_text(**model_input, progress_bar=my_bar)
+        st.markdown("<h1 style='text-align: center;'>Classification completed!</h1>", unsafe_allow_html=True)
+        small_categories = []
+        cat, proba = model_result[0]
+        st.write(r"$\textsf{\Large " + f'{cat}: {round(100*proba)}' + r"\%}$")
+        for cat, proba in model_result[1:]:
+            if proba < 0.1:
+                small_categories.append(f'{cat}: {round(100*proba, 1)}' + r"\%")
+            else:
+                st.write(r"$\textsf{\large " + f'{cat}: {round(100*proba)}' + r"\%}$")
+        if small_categories:
+            st.write(', '.join(small_categories))
+
+
+
+
+

categories_from_model.json

@@ -0,0 +1 @@
+["adap-org", "astro-ph", "astro-ph.CO", "astro-ph.EP", "astro-ph.GA", "astro-ph.IM", "astro-ph.SR", "cmp-lg", "cond-mat", "cond-mat.dis-nn", "cond-mat.mtrl-sci", "cond-mat.other", "cond-mat.soft", "cond-mat.stat-mech", "cond-mat.supr-con", "cs.AI", "cs.AR", "cs.CC", "cs.CE", "cs.CG", "cs.CL", "cs.CR", "cs.CV", "cs.CY", "cs.DB", "cs.DC", "cs.DL", "cs.DM", "cs.DS", "cs.ET", "cs.FL", "cs.GL", "cs.GR", "cs.GT", "cs.HC", "cs.IR", "cs.IT", "cs.LG", "cs.LO", "cs.MA", "cs.MM", "cs.MS", "cs.NA", "cs.NE", "cs.NI", "cs.OH", "cs.OS", "cs.PF", "cs.PL", "cs.RO", "cs.SC", "cs.SD", "cs.SE", "cs.SI", "cs.SY", "econ.EM", "eess.AS", "eess.IV", "eess.SP", "gr-qc", "hep-ex", "hep-lat", "hep-ph", "hep-th", "math.AG", "math.AP", "math.AT", "math.CA", "math.CO", "math.CT", "math.DG", "math.DS", "math.FA", "math.GM", "math.GN", "math.GR", "math.GT", "math.HO", "math.LO", "math.MG", "math.NA", "math.NT", "math.OC", "math.PR", "math.RA", "math.RT", "math.ST", "nlin.AO", "nlin.CD", "nlin.CG", "nlin.PS", "nucl-th", "physics.ao-ph", "physics.bio-ph", "physics.chem-ph", "physics.class-ph", "physics.comp-ph", "physics.data-an", "physics.gen-ph", "physics.geo-ph", "physics.hist-ph", "physics.ins-det", "physics.med-ph", "physics.optics", "physics.soc-ph", "q-bio.BM", "q-bio.CB", "q-bio.GN", "q-bio.MN", "q-bio.NC", "q-bio.PE", "q-bio.QM", "q-bio.TO", "q-fin.CP", "q-fin.EC", "q-fin.GN", "q-fin.PM", "q-fin.RM", "q-fin.ST", "q-fin.TR", "quant-ph", "stat.AP", "stat.CO", "stat.ME", "stat.ML", "stat.OT"]

categories_with_names.json

@@ -0,0 +1,159 @@
+{"cs.AI": "Artificial Intelligence",
+"cs.AR": "Hardware Architecture",
+"cs.CC": "Computational Complexity",
+"cs.CE": "Computational Engineering, Finance, and Science",
+"cs.CG": "Computational Geometry",
+"cs.CL": "Computation and Language",
+"cs.CR": "Cryptography and Security",
+"cs.CV": "Computer Vision and Pattern Recognition",
+"cs.CY": "Computers and Society",
+"cs.DB": "Databases",
+"cs.DC": "Distributed, Parallel, and Cluster Computing",
+"cs.DL": "Digital Libraries",
+"cs.DM": "Discrete Mathematics",
+"cs.DS": "Data Structures and Algorithms",
+"cs.ET": "Emerging Technologies",
+"cs.FL": "Formal Languages and Automata Theory",
+"cs.GL": "General Literature",
+"cs.GR": "Graphics",
+"cs.GT": "Computer Science and Game Theory",
+"cs.HC": "Human-Computer Interaction",
+"cs.IR": "Information Retrieval",
+"cs.IT": "Information Theory",
+"cs.LG": "Machine Learning",
+"cs.LO": "Logic in Computer Science",
+"cs.MA": "Multiagent Systems",
+"cs.MM": "Multimedia",
+"cs.MS": "Mathematical Software",
+"cs.NA": "Numerical Analysis",
+"cs.NE": "Neural and Evolutionary Computing",
+"cs.NI": "Networking and Internet Architecture",
+"cs.OH": "Other Computer Science",
+"cs.OS": "Operating Systems",
+"cs.PF": "Performance",
+"cs.PL": "Programming Languages",
+"cs.RO": "Robotics",
+"cs.SC": "Symbolic Computation",
+"cs.SD": "Sound",
+"cs.SE": "Software Engineering",
+"cs.SI": "Social and Information Networks",
+"cs.SY": "Systems and Control",
+"econ.EM": "Econometrics",
+"econ.GN": "General Economics",
+"econ.TH": "Theoretical Economics",
+"eess.AS": "Audio and Speech Processing",
+"eess.IV": "Image and Video Processing",
+"eess.SP": "Signal Processing",
+"eess.SY": "Systems and Control",
+"math.AC": "Commutative Algebra",
+"math.AG": "Algebraic Geometry",
+"math.AP": "Analysis of PDEs",
+"math.AT": "Algebraic Topology",
+"math.CA": "Classical Analysis and ODEs",
+"math.CO": "Combinatorics",
+"math.CT": "Category Theory",
+"math.CV": "Complex Variables",
+"math.DG": "Differential Geometry",
+"math.DS": "Dynamical Systems",
+"math.FA": "Functional Analysis",
+"math.GM": "General Mathematics",
+"math.GN": "General Topology",
+"math.GR": "Group Theory",
+"math.GT": "Geometric Topology",
+"math.HO": "History and Overview",
+"math.IT": "Information Theory",
+"math.KT": "K-Theory and Homology",
+"math.LO": "Logic",
+"math.MG": "Metric Geometry",
+"math.MP": "Mathematical Physics",
+"math.NA": "Numerical Analysis",
+"math.NT": "Number Theory",
+"math.OA": "Operator Algebras",
+"math.OC": "Optimization and Control",
+"math.PR": "Probability",
+"math.QA": "Quantum Algebra",
+"math.RA": "Rings and Algebras",
+"math.RT": "Representation Theory",
+"math.SG": "Symplectic Geometry",
+"math.SP": "Spectral Theory",
+"math.ST": "Statistics Theory",
+"astro-ph.CO": "Cosmology and Nongalactic Astrophysics",
+"astro-ph.EP": "Earth and Planetary Astrophysics",
+"astro-ph.GA": "Astrophysics of Galaxies",
+"astro-ph.HE": "High Energy Astrophysical Phenomena",
+"astro-ph.IM": "Instrumentation and Methods for Astrophysics",
+"astro-ph.SR": "Solar and Stellar Astrophysics",
+"cond-mat.dis-nn": "Disordered Systems and Neural Networks",
+"cond-mat.mes-hall": "Mesoscale and Nanoscale Physics",
+"cond-mat.mtrl-sci": "Materials Science",
+"cond-mat.other": "Other Condensed Matter",
+"cond-mat.quant-gas": "Quantum Gases",
+"cond-mat.soft": "Soft Condensed Matter",
+"cond-mat.stat-mech": "Statistical Mechanics",
+"cond-mat.str-el": "Strongly Correlated Electrons",
+"cond-mat.supr-con": "Superconductivity",
+"gr-qc": "General Relativity and Quantum Cosmology",
+"hep-ex": "High Energy Physics - Experiment",
+"hep-lat": "High Energy Physics - Lattice",
+"hep-ph": "High Energy Physics - Phenomenology",
+"hep-th": "High Energy Physics - Theory",
+"math-ph": "Mathematical Physics",
+"nlin.AO": "Adaptation and Self-Organizing Systems",
+"nlin.CD": "Chaotic Dynamics",
+"nlin.CG": "Cellular Automata and Lattice Gases",
+"nlin.PS": "Pattern Formation and Solitons",
+"nlin.SI": "Exactly Solvable and Integrable Systems",
+"nucl-ex": "Nuclear Experiment",
+"nucl-th": "Nuclear Theory",
+"physics.acc-ph": "Accelerator Physics",
+"physics.ao-ph": "Atmospheric and Oceanic Physics",
+"physics.app-ph": "Applied Physics",
+"physics.atm-clus": "Atomic and Molecular Clusters",
+"physics.atom-ph": "Atomic Physics",
+"physics.bio-ph": "Biological Physics",
+"physics.chem-ph": "Chemical Physics",
+"physics.class-ph": "Classical Physics",
+"physics.comp-ph": "Computational Physics",
+"physics.data-an": "Data Analysis, Statistics and Probability",
+"physics.ed-ph": "Physics Education",
+"physics.flu-dyn": "Fluid Dynamics",
+"physics.gen-ph": "General Physics",
+"physics.geo-ph": "Geophysics",
+"physics.hist-ph": "History and Philosophy of Physics",
+"physics.ins-det": "Instrumentation and Detectors",
+"physics.med-ph": "Medical Physics",
+"physics.optics": "Optics",
+"physics.plasm-ph": "Plasma Physics",
+"physics.pop-ph": "Popular Physics",
+"physics.soc-ph": "Physics and Society",
+"physics.space-ph": "Space Physics",
+"quant-ph": "Quantum Physics",
+"q-bio.BM": "Biomolecules",
+"q-bio.CB": "Cell Behavior",
+"q-bio.GN": "Genomics",
+"q-bio.MN": "Molecular Networks",
+"q-bio.NC": "Neurons and Cognition",
+"q-bio.OT": "Other Quantitative Biology",
+"q-bio.PE": "Populations and Evolution",
+"q-bio.QM": "Quantitative Methods",
+"q-bio.SC": "Subcellular Processes",
+"q-bio.TO": "Tissues and Organs",
+"q-fin.CP": "Computational Finance",
+"q-fin.EC": "Economics",
+"q-fin.GN": "General Finance",
+"q-fin.MF": "Mathematical Finance",
+"q-fin.PM": "Portfolio Management",
+"q-fin.PR": "Pricing of Securities",
+"q-fin.RM": "Risk Management",
+"q-fin.ST": "Statistical Finance",
+"q-fin.TR": "Trading and Market Microstructure",
+"stat.AP": "Applications",
+"stat.CO": "Computation",
+"stat.ME": "Methodology",
+"stat.ML": "Machine Learning",
+"stat.OT": "Other Statistics",
+"stat.TH": "Statistics Theory",
+"astro-ph": "Astrophysics",
+"adap-org": "Adaptation and Self-Organizing Systems",
+"cmp-lg": "Computation and Language",
+"cond-mat": "Condensed Matter"}

powerful_model_abstracts/checkpoint-13472/config.json

@@ -0,0 +1,281 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "adap-org",
+    "1": "astro-ph",
+    "2": "astro-ph.CO",
+    "3": "astro-ph.EP",
+    "4": "astro-ph.GA",
+    "5": "astro-ph.IM",
+    "6": "astro-ph.SR",
+    "7": "cmp-lg",
+    "8": "cond-mat",
+    "9": "cond-mat.dis-nn",
+    "10": "cond-mat.mtrl-sci",
+    "11": "cond-mat.other",
+    "12": "cond-mat.soft",
+    "13": "cond-mat.stat-mech",
+    "14": "cond-mat.supr-con",
+    "15": "cs.AI",
+    "16": "cs.AR",
+    "17": "cs.CC",
+    "18": "cs.CE",
+    "19": "cs.CG",
+    "20": "cs.CL",
+    "21": "cs.CR",
+    "22": "cs.CV",
+    "23": "cs.CY",
+    "24": "cs.DB",
+    "25": "cs.DC",
+    "26": "cs.DL",
+    "27": "cs.DM",
+    "28": "cs.DS",
+    "29": "cs.ET",
+    "30": "cs.FL",
+    "31": "cs.GL",
+    "32": "cs.GR",
+    "33": "cs.GT",
+    "34": "cs.HC",
+    "35": "cs.IR",
+    "36": "cs.IT",
+    "37": "cs.LG",
+    "38": "cs.LO",
+    "39": "cs.MA",
+    "40": "cs.MM",
+    "41": "cs.MS",
+    "42": "cs.NA",
+    "43": "cs.NE",
+    "44": "cs.NI",
+    "45": "cs.OH",
+    "46": "cs.OS",
+    "47": "cs.PF",
+    "48": "cs.PL",
+    "49": "cs.RO",
+    "50": "cs.SC",
+    "51": "cs.SD",
+    "52": "cs.SE",
+    "53": "cs.SI",
+    "54": "cs.SY",
+    "55": "econ.EM",
+    "56": "eess.AS",
+    "57": "eess.IV",
+    "58": "eess.SP",
+    "59": "gr-qc",
+    "60": "hep-ex",
+    "61": "hep-lat",
+    "62": "hep-ph",
+    "63": "hep-th",
+    "64": "math.AG",
+    "65": "math.AP",
+    "66": "math.AT",
+    "67": "math.CA",
+    "68": "math.CO",
+    "69": "math.CT",
+    "70": "math.DG",
+    "71": "math.DS",
+    "72": "math.FA",
+    "73": "math.GM",
+    "74": "math.GN",
+    "75": "math.GR",
+    "76": "math.GT",
+    "77": "math.HO",
+    "78": "math.LO",
+    "79": "math.MG",
+    "80": "math.NA",
+    "81": "math.NT",
+    "82": "math.OC",
+    "83": "math.PR",
+    "84": "math.RA",
+    "85": "math.RT",
+    "86": "math.ST",
+    "87": "nlin.AO",
+    "88": "nlin.CD",
+    "89": "nlin.CG",
+    "90": "nlin.PS",
+    "91": "nucl-th",
+    "92": "physics.ao-ph",
+    "93": "physics.bio-ph",
+    "94": "physics.chem-ph",
+    "95": "physics.class-ph",
+    "96": "physics.comp-ph",
+    "97": "physics.data-an",
+    "98": "physics.gen-ph",
+    "99": "physics.geo-ph",
+    "100": "physics.hist-ph",
+    "101": "physics.ins-det",
+    "102": "physics.med-ph",
+    "103": "physics.optics",
+    "104": "physics.soc-ph",
+    "105": "q-bio.BM",
+    "106": "q-bio.CB",
+    "107": "q-bio.GN",
+    "108": "q-bio.MN",
+    "109": "q-bio.NC",
+    "110": "q-bio.PE",
+    "111": "q-bio.QM",
+    "112": "q-bio.TO",
+    "113": "q-fin.CP",
+    "114": "q-fin.EC",
+    "115": "q-fin.GN",
+    "116": "q-fin.PM",
+    "117": "q-fin.RM",
+    "118": "q-fin.ST",
+    "119": "q-fin.TR",
+    "120": "quant-ph",
+    "121": "stat.AP",
+    "122": "stat.CO",
+    "123": "stat.ME",
+    "124": "stat.ML",
+    "125": "stat.OT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "adap-org": 0,
+    "astro-ph": 1,
+    "astro-ph.CO": 2,
+    "astro-ph.EP": 3,
+    "astro-ph.GA": 4,
+    "astro-ph.IM": 5,
+    "astro-ph.SR": 6,
+    "cmp-lg": 7,
+    "cond-mat": 8,
+    "cond-mat.dis-nn": 9,
+    "cond-mat.mtrl-sci": 10,
+    "cond-mat.other": 11,
+    "cond-mat.soft": 12,
+    "cond-mat.stat-mech": 13,
+    "cond-mat.supr-con": 14,
+    "cs.AI": 15,
+    "cs.AR": 16,
+    "cs.CC": 17,
+    "cs.CE": 18,
+    "cs.CG": 19,
+    "cs.CL": 20,
+    "cs.CR": 21,
+    "cs.CV": 22,
+    "cs.CY": 23,
+    "cs.DB": 24,
+    "cs.DC": 25,
+    "cs.DL": 26,
+    "cs.DM": 27,
+    "cs.DS": 28,
+    "cs.ET": 29,
+    "cs.FL": 30,
+    "cs.GL": 31,
+    "cs.GR": 32,
+    "cs.GT": 33,
+    "cs.HC": 34,
+    "cs.IR": 35,
+    "cs.IT": 36,
+    "cs.LG": 37,
+    "cs.LO": 38,
+    "cs.MA": 39,
+    "cs.MM": 40,
+    "cs.MS": 41,
+    "cs.NA": 42,
+    "cs.NE": 43,
+    "cs.NI": 44,
+    "cs.OH": 45,
+    "cs.OS": 46,
+    "cs.PF": 47,
+    "cs.PL": 48,
+    "cs.RO": 49,
+    "cs.SC": 50,
+    "cs.SD": 51,
+    "cs.SE": 52,
+    "cs.SI": 53,
+    "cs.SY": 54,
+    "econ.EM": 55,
+    "eess.AS": 56,
+    "eess.IV": 57,
+    "eess.SP": 58,
+    "gr-qc": 59,
+    "hep-ex": 60,
+    "hep-lat": 61,
+    "hep-ph": 62,
+    "hep-th": 63,
+    "math.AG": 64,
+    "math.AP": 65,
+    "math.AT": 66,
+    "math.CA": 67,
+    "math.CO": 68,
+    "math.CT": 69,
+    "math.DG": 70,
+    "math.DS": 71,
+    "math.FA": 72,
+    "math.GM": 73,
+    "math.GN": 74,
+    "math.GR": 75,
+    "math.GT": 76,
+    "math.HO": 77,
+    "math.LO": 78,
+    "math.MG": 79,
+    "math.NA": 80,
+    "math.NT": 81,
+    "math.OC": 82,
+    "math.PR": 83,
+    "math.RA": 84,
+    "math.RT": 85,
+    "math.ST": 86,
+    "nlin.AO": 87,
+    "nlin.CD": 88,
+    "nlin.CG": 89,
+    "nlin.PS": 90,
+    "nucl-th": 91,
+    "physics.ao-ph": 92,
+    "physics.bio-ph": 93,
+    "physics.chem-ph": 94,
+    "physics.class-ph": 95,
+    "physics.comp-ph": 96,
+    "physics.data-an": 97,
+    "physics.gen-ph": 98,
+    "physics.geo-ph": 99,
+    "physics.hist-ph": 100,
+    "physics.ins-det": 101,
+    "physics.med-ph": 102,
+    "physics.optics": 103,
+    "physics.soc-ph": 104,
+    "q-bio.BM": 105,
+    "q-bio.CB": 106,
+    "q-bio.GN": 107,
+    "q-bio.MN": 108,
+    "q-bio.NC": 109,
+    "q-bio.PE": 110,
+    "q-bio.QM": 111,
+    "q-bio.TO": 112,
+    "q-fin.CP": 113,
+    "q-fin.EC": 114,
+    "q-fin.GN": 115,
+    "q-fin.PM": 116,
+    "q-fin.RM": 117,
+    "q-fin.ST": 118,
+    "q-fin.TR": 119,
+    "quant-ph": 120,
+    "stat.AP": 121,
+    "stat.CO": 122,
+    "stat.ME": 123,
+    "stat.ML": 124,
+    "stat.OT": 125
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

powerful_model_abstracts/checkpoint-13472/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31017a376090f42d5ad1bda9cddb0f4ab56464c87a863166e4d426d264e3bbb5
+size 438340072

powerful_model_titles/checkpoint-13472/config.json

@@ -0,0 +1,281 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "adap-org",
+    "1": "astro-ph",
+    "2": "astro-ph.CO",
+    "3": "astro-ph.EP",
+    "4": "astro-ph.GA",
+    "5": "astro-ph.IM",
+    "6": "astro-ph.SR",
+    "7": "cmp-lg",
+    "8": "cond-mat",
+    "9": "cond-mat.dis-nn",
+    "10": "cond-mat.mtrl-sci",
+    "11": "cond-mat.other",
+    "12": "cond-mat.soft",
+    "13": "cond-mat.stat-mech",
+    "14": "cond-mat.supr-con",
+    "15": "cs.AI",
+    "16": "cs.AR",
+    "17": "cs.CC",
+    "18": "cs.CE",
+    "19": "cs.CG",
+    "20": "cs.CL",
+    "21": "cs.CR",
+    "22": "cs.CV",
+    "23": "cs.CY",
+    "24": "cs.DB",
+    "25": "cs.DC",
+    "26": "cs.DL",
+    "27": "cs.DM",
+    "28": "cs.DS",
+    "29": "cs.ET",
+    "30": "cs.FL",
+    "31": "cs.GL",
+    "32": "cs.GR",
+    "33": "cs.GT",
+    "34": "cs.HC",
+    "35": "cs.IR",
+    "36": "cs.IT",
+    "37": "cs.LG",
+    "38": "cs.LO",
+    "39": "cs.MA",
+    "40": "cs.MM",
+    "41": "cs.MS",
+    "42": "cs.NA",
+    "43": "cs.NE",
+    "44": "cs.NI",
+    "45": "cs.OH",
+    "46": "cs.OS",
+    "47": "cs.PF",
+    "48": "cs.PL",
+    "49": "cs.RO",
+    "50": "cs.SC",
+    "51": "cs.SD",
+    "52": "cs.SE",
+    "53": "cs.SI",
+    "54": "cs.SY",
+    "55": "econ.EM",
+    "56": "eess.AS",
+    "57": "eess.IV",
+    "58": "eess.SP",
+    "59": "gr-qc",
+    "60": "hep-ex",
+    "61": "hep-lat",
+    "62": "hep-ph",
+    "63": "hep-th",
+    "64": "math.AG",
+    "65": "math.AP",
+    "66": "math.AT",
+    "67": "math.CA",
+    "68": "math.CO",
+    "69": "math.CT",
+    "70": "math.DG",
+    "71": "math.DS",
+    "72": "math.FA",
+    "73": "math.GM",
+    "74": "math.GN",
+    "75": "math.GR",
+    "76": "math.GT",
+    "77": "math.HO",
+    "78": "math.LO",
+    "79": "math.MG",
+    "80": "math.NA",
+    "81": "math.NT",
+    "82": "math.OC",
+    "83": "math.PR",
+    "84": "math.RA",
+    "85": "math.RT",
+    "86": "math.ST",
+    "87": "nlin.AO",
+    "88": "nlin.CD",
+    "89": "nlin.CG",
+    "90": "nlin.PS",
+    "91": "nucl-th",
+    "92": "physics.ao-ph",
+    "93": "physics.bio-ph",
+    "94": "physics.chem-ph",
+    "95": "physics.class-ph",
+    "96": "physics.comp-ph",
+    "97": "physics.data-an",
+    "98": "physics.gen-ph",
+    "99": "physics.geo-ph",
+    "100": "physics.hist-ph",
+    "101": "physics.ins-det",
+    "102": "physics.med-ph",
+    "103": "physics.optics",
+    "104": "physics.soc-ph",
+    "105": "q-bio.BM",
+    "106": "q-bio.CB",
+    "107": "q-bio.GN",
+    "108": "q-bio.MN",
+    "109": "q-bio.NC",
+    "110": "q-bio.PE",
+    "111": "q-bio.QM",
+    "112": "q-bio.TO",
+    "113": "q-fin.CP",
+    "114": "q-fin.EC",
+    "115": "q-fin.GN",
+    "116": "q-fin.PM",
+    "117": "q-fin.RM",
+    "118": "q-fin.ST",
+    "119": "q-fin.TR",
+    "120": "quant-ph",
+    "121": "stat.AP",
+    "122": "stat.CO",
+    "123": "stat.ME",
+    "124": "stat.ML",
+    "125": "stat.OT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "adap-org": 0,
+    "astro-ph": 1,
+    "astro-ph.CO": 2,
+    "astro-ph.EP": 3,
+    "astro-ph.GA": 4,
+    "astro-ph.IM": 5,
+    "astro-ph.SR": 6,
+    "cmp-lg": 7,
+    "cond-mat": 8,
+    "cond-mat.dis-nn": 9,
+    "cond-mat.mtrl-sci": 10,
+    "cond-mat.other": 11,
+    "cond-mat.soft": 12,
+    "cond-mat.stat-mech": 13,
+    "cond-mat.supr-con": 14,
+    "cs.AI": 15,
+    "cs.AR": 16,
+    "cs.CC": 17,
+    "cs.CE": 18,
+    "cs.CG": 19,
+    "cs.CL": 20,
+    "cs.CR": 21,
+    "cs.CV": 22,
+    "cs.CY": 23,
+    "cs.DB": 24,
+    "cs.DC": 25,
+    "cs.DL": 26,
+    "cs.DM": 27,
+    "cs.DS": 28,
+    "cs.ET": 29,
+    "cs.FL": 30,
+    "cs.GL": 31,
+    "cs.GR": 32,
+    "cs.GT": 33,
+    "cs.HC": 34,
+    "cs.IR": 35,
+    "cs.IT": 36,
+    "cs.LG": 37,
+    "cs.LO": 38,
+    "cs.MA": 39,
+    "cs.MM": 40,
+    "cs.MS": 41,
+    "cs.NA": 42,
+    "cs.NE": 43,
+    "cs.NI": 44,
+    "cs.OH": 45,
+    "cs.OS": 46,
+    "cs.PF": 47,
+    "cs.PL": 48,
+    "cs.RO": 49,
+    "cs.SC": 50,
+    "cs.SD": 51,
+    "cs.SE": 52,
+    "cs.SI": 53,
+    "cs.SY": 54,
+    "econ.EM": 55,
+    "eess.AS": 56,
+    "eess.IV": 57,
+    "eess.SP": 58,
+    "gr-qc": 59,
+    "hep-ex": 60,
+    "hep-lat": 61,
+    "hep-ph": 62,
+    "hep-th": 63,
+    "math.AG": 64,
+    "math.AP": 65,
+    "math.AT": 66,
+    "math.CA": 67,
+    "math.CO": 68,
+    "math.CT": 69,
+    "math.DG": 70,
+    "math.DS": 71,
+    "math.FA": 72,
+    "math.GM": 73,
+    "math.GN": 74,
+    "math.GR": 75,
+    "math.GT": 76,
+    "math.HO": 77,
+    "math.LO": 78,
+    "math.MG": 79,
+    "math.NA": 80,
+    "math.NT": 81,
+    "math.OC": 82,
+    "math.PR": 83,
+    "math.RA": 84,
+    "math.RT": 85,
+    "math.ST": 86,
+    "nlin.AO": 87,
+    "nlin.CD": 88,
+    "nlin.CG": 89,
+    "nlin.PS": 90,
+    "nucl-th": 91,
+    "physics.ao-ph": 92,
+    "physics.bio-ph": 93,
+    "physics.chem-ph": 94,
+    "physics.class-ph": 95,
+    "physics.comp-ph": 96,
+    "physics.data-an": 97,
+    "physics.gen-ph": 98,
+    "physics.geo-ph": 99,
+    "physics.hist-ph": 100,
+    "physics.ins-det": 101,
+    "physics.med-ph": 102,
+    "physics.optics": 103,
+    "physics.soc-ph": 104,
+    "q-bio.BM": 105,
+    "q-bio.CB": 106,
+    "q-bio.GN": 107,
+    "q-bio.MN": 108,
+    "q-bio.NC": 109,
+    "q-bio.PE": 110,
+    "q-bio.QM": 111,
+    "q-bio.TO": 112,
+    "q-fin.CP": 113,
+    "q-fin.EC": 114,
+    "q-fin.GN": 115,
+    "q-fin.PM": 116,
+    "q-fin.RM": 117,
+    "q-fin.ST": 118,
+    "q-fin.TR": 119,
+    "quant-ph": 120,
+    "stat.AP": 121,
+    "stat.CO": 122,
+    "stat.ME": 123,
+    "stat.ML": 124,
+    "stat.OT": 125
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

powerful_model_titles/checkpoint-13472/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245a73ba7b8f454bf53f90b354101db69b44d9100e152d6abe06dc47a408a548
+size 438340072