Upload 5 files

app.py

@@ -0,0 +1,80 @@
+import streamlit as st
+
+from transformers import AutoTokenizer, DistilBertForSequenceClassification
+import torch
+from torch.nn.functional import softmax
+
+
+
+base_model_name = 'distilbert-base-uncased'
+
+@st.cache
+def load_tags_info():
+    tag_to_id = {}
+    id_to_tag = {}
+    id_to_description = {}
+    with open('tags.txt', 'r') as file:
+        i = 0
+        for line in file:
+            
+            space = line.find(' ')
+            
+            tag = line[:space]
+            description = line[space+1:-1]
+            
+            tag_to_id[tag] = i
+            id_to_tag[i] = tag
+            id_to_description[i] = description
+            
+            i += 1
+    
+    return (tag_to_id, id_to_tag, id_to_description)
+
+tag_to_id, id_to_tag, id_to_description = load_tags_info()
+
+@st.cache
+def load_model():
+    return DistilBertForSequenceClassification.from_pretrained('./')
+
+def load_tokenizer():
+    return AutoTokenizer.from_pretrained('distilbert-base-uncased')
+
+def top_xx(preds, xx=95):
+    tops = torch.argsort(preds, 1, descending=True)
+    total = 0
+    index = 0
+    result = []
+    while total < xx / 100:
+        next_id = tops[0, index].item()
+        total += preds[0, next_id]
+        index += 1
+        result.append({'tag': id_to_tag[next_id], 'description': id_to_description[next_id]})
+    return result
+
+model = load_model()
+tokenizer = load_tokenizer()
+temperature = 1
+
+st.title('ArXivTaxonomizer&copy; (original version)')
+st.caption('If you are aware of any other public services which are  illegally providing the ArXivTaxonomizer&copy; functionality, please consider informing us.')
+
+with st.form("Taxonomizer"):
+    
+    title = st.text_area(label='Title', height=30)
+    abstract = st.text_area(label='Abstract (optional)', height=200)
+    st.caption('Lower values will generate a few best guesses. Higher values will lead to a comprehensive list of topics that our model considers relevant. \nEmpirically, values arond 70 work best and generate a list of 3-5 guesses.')
+
+    submitted = st.form_submit_button("Taxonomize")
+    st.caption('We **do not** recommend using ArXivTaxonomizer&copy; to choose tags for you new paper.')
+    if submitted:
+        if title == '':
+            st.markdown("You are most definitely abusing our service. Have the decency to at least enter a title.")
+        else:
+            prompt = 'Title: ' + title + ' Abstract: ' + abstract
+            tokens = tokenizer(prompt, truncation=True, padding='max_length', return_tensors='pt')['input_ids']
+            preds = softmax(model(tokens.reshape(1, -1)).logits / temperature, dim=1)
+            tags = top_xx(preds)
+            other_tags = []
+            st.header('Inferred tags:')
+            for i, tag_data in enumerate(tags):
+                    st.markdown('* ' + tag_data['tag'] + ' (' + tag_data['description'] + ')')   

config.json

@@ -0,0 +1,338 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90",
+    "91": "LABEL_91",
+    "92": "LABEL_92",
+    "93": "LABEL_93",
+    "94": "LABEL_94",
+    "95": "LABEL_95",
+    "96": "LABEL_96",
+    "97": "LABEL_97",
+    "98": "LABEL_98",
+    "99": "LABEL_99",
+    "100": "LABEL_100",
+    "101": "LABEL_101",
+    "102": "LABEL_102",
+    "103": "LABEL_103",
+    "104": "LABEL_104",
+    "105": "LABEL_105",
+    "106": "LABEL_106",
+    "107": "LABEL_107",
+    "108": "LABEL_108",
+    "109": "LABEL_109",
+    "110": "LABEL_110",
+    "111": "LABEL_111",
+    "112": "LABEL_112",
+    "113": "LABEL_113",
+    "114": "LABEL_114",
+    "115": "LABEL_115",
+    "116": "LABEL_116",
+    "117": "LABEL_117",
+    "118": "LABEL_118",
+    "119": "LABEL_119",
+    "120": "LABEL_120",
+    "121": "LABEL_121",
+    "122": "LABEL_122",
+    "123": "LABEL_123",
+    "124": "LABEL_124",
+    "125": "LABEL_125",
+    "126": "LABEL_126",
+    "127": "LABEL_127",
+    "128": "LABEL_128",
+    "129": "LABEL_129",
+    "130": "LABEL_130",
+    "131": "LABEL_131",
+    "132": "LABEL_132",
+    "133": "LABEL_133",
+    "134": "LABEL_134",
+    "135": "LABEL_135",
+    "136": "LABEL_136",
+    "137": "LABEL_137",
+    "138": "LABEL_138",
+    "139": "LABEL_139",
+    "140": "LABEL_140",
+    "141": "LABEL_141",
+    "142": "LABEL_142",
+    "143": "LABEL_143",
+    "144": "LABEL_144",
+    "145": "LABEL_145",
+    "146": "LABEL_146",
+    "147": "LABEL_147",
+    "148": "LABEL_148",
+    "149": "LABEL_149",
+    "150": "LABEL_150",
+    "151": "LABEL_151",
+    "152": "LABEL_152",
+    "153": "LABEL_153",
+    "154": "LABEL_154"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_150": 150,
+    "LABEL_151": 151,
+    "LABEL_152": 152,
+    "LABEL_153": 153,
+    "LABEL_154": 154,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8f30540e3f618551d9d8a2c2f8a76cfcf9008187df7526eeab7a6e4d731c9d
+size 268326125

tags.txt

@@ -0,0 +1,155 @@
+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