Hugging Face's logo

Spaces:
Utiuzhnikov
/
v2
Runtime error

App Files Community
1

try

#1
by Utiuzhnikov - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+37
-61741
Files changed (19) hide show
  1. requirements.txt +3 -9
  2. src/model/config.json +0 -54
  3. src/model/id2label.json +0 -13
  4. src/model/label2id.json +0 -13
  5. src/model/label_full.json +0 -13
  6. src/model/model.safetensors +0 -3
  7. src/model/tokenizer.json +0 -0
  8. src/model/tokenizer_config.json +0 -14
  9. src/model_v2/config.json +0 -277
  10. src/model_v2/id2label.json +0 -124
  11. src/model_v2/label2id.json +0 -124
  12. src/model_v2/label_full.json +0 -130
  13. src/model_v2/model-00001-of-00003.safetensors +0 -3
  14. src/model_v2/model-00002-of-00003.safetensors +0 -3
  15. src/model_v2/model-00003-of-00003.safetensors +0 -3
  16. src/model_v2/model.safetensors.index.json +0 -209
  17. src/model_v2/tokenizer.json +0 -0
  18. src/model_v2/tokenizer_config.json +0 -21
  19. src/streamlit_app.py +34 -328
requirements.txt CHANGED
@@ -1,9 +1,3 @@
1
- torch>=2.0.0
2
- transformers>=4.30.0
3
- datasets>=2.0.0
4
- scikit-learn>=1.0.0
5
- numpy>=1.24.0
6
- pandas>=1.5.0
7
- matplotlib>=3.5.0
8
- streamlit>=1.20.0
9
- accelerate>=0.20.0
 
1
+ altair
2
+ pandas
3
+ streamlit
 
 
 
 
 
 
src/model/config.json DELETED
@@ -1,54 +0,0 @@
1
- {
2
- "activation": "gelu",
3
- "architectures": [
4
- "DistilBertForSequenceClassification"
5
- ],
6
- "attention_dropout": 0.1,
7
- "bos_token_id": null,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "dtype": "float32",
11
- "eos_token_id": null,
12
- "hidden_dim": 3072,
13
- "id2label": {
14
- "0": "math.AC",
15
- "1": "cs.CV",
16
- "2": "cs.AI",
17
- "3": "cs.SY",
18
- "4": "math.GR",
19
- "5": "cs.CE",
20
- "6": "cs.PL",
21
- "7": "cs.IT",
22
- "8": "cs.DS",
23
- "9": "cs.NE",
24
- "10": "math.ST"
25
- },
26
- "initializer_range": 0.02,
27
- "label2id": {
28
- "cs.AI": 2,
29
- "cs.CE": 5,
30
- "cs.CV": 1,
31
- "cs.DS": 8,
32
- "cs.IT": 7,
33
- "cs.NE": 9,
34
- "cs.PL": 6,
35
- "cs.SY": 3,
36
- "math.AC": 0,
37
- "math.GR": 4,
38
- "math.ST": 10
39
- },
40
- "max_position_embeddings": 512,
41
- "model_type": "distilbert",
42
- "n_heads": 12,
43
- "n_layers": 6,
44
- "output_past": true,
45
- "pad_token_id": 0,
46
- "problem_type": "single_label_classification",
47
- "qa_dropout": 0.1,
48
- "seq_classif_dropout": 0.2,
49
- "sinusoidal_pos_embds": false,
50
- "tie_weights_": true,
51
- "tie_word_embeddings": true,
52
- "transformers_version": "5.5.0",
53
- "vocab_size": 28996
54
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model/id2label.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "0": "math.AC",
3
- "1": "cs.CV",
4
- "2": "cs.AI",
5
- "3": "cs.SY",
6
- "4": "math.GR",
7
- "5": "cs.CE",
8
- "6": "cs.PL",
9
- "7": "cs.IT",
10
- "8": "cs.DS",
11
- "9": "cs.NE",
12
- "10": "math.ST"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model/label2id.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "math.AC": 0,
3
- "cs.CV": 1,
4
- "cs.AI": 2,
5
- "cs.SY": 3,
6
- "math.GR": 4,
7
- "cs.CE": 5,
8
- "cs.PL": 6,
9
- "cs.IT": 7,
10
- "cs.DS": 8,
11
- "cs.NE": 9,
12
- "math.ST": 10
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model/label_full.json DELETED
@@ -1,13 +0,0 @@
1
- {
2
- "math.AC": "Mathematics: Commutative Algebra",
3
- "cs.CV": "Computer Science: Computer Vision",
4
- "cs.AI": "Computer Science: Artificial Intelligence",
5
- "cs.SY": "Computer Science: Systems & Control",
6
- "math.GR": "Mathematics: Group Theory",
7
- "cs.CE": "Computer Science: Computational Engineering",
8
- "cs.PL": "Computer Science: Programming Languages",
9
- "cs.IT": "Computer Science: Information Theory",
10
- "cs.DS": "Computer Science: Data Structures & Algorithms",
11
- "cs.NE": "Computer Science: Neural & Evolutionary Computing",
12
- "math.ST": "Mathematics: Statistics Theory"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:424b45ffb940c6391d3acc08474a706c2b83c3b49c57db9ba7fbdbaa0698d8cd
3
- size 263172372
 
 
 
 
src/model/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
src/model/tokenizer_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "cls_token": "[CLS]",
4
- "do_lower_case": false,
5
- "is_local": false,
6
- "mask_token": "[MASK]",
7
- "model_max_length": 512,
8
- "pad_token": "[PAD]",
9
- "sep_token": "[SEP]",
10
- "strip_accents": null,
11
- "tokenize_chinese_chars": true,
12
- "tokenizer_class": "BertTokenizer",
13
- "unk_token": "[UNK]"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model_v2/config.json DELETED
@@ -1,277 +0,0 @@
1
- {
2
- "add_cross_attention": false,
3
- "architectures": [
4
- "BertForSequenceClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": null,
8
- "classifier_dropout": null,
9
- "dtype": "float32",
10
- "eos_token_id": null,
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
- "id2label": {
15
- "0": "astro-ph.CO",
16
- "1": "astro-ph.EP",
17
- "2": "astro-ph.GA",
18
- "3": "astro-ph.HE",
19
- "4": "astro-ph.IM",
20
- "5": "astro-ph.SR",
21
- "6": "cond-mat.dis-nn",
22
- "7": "cond-mat.mes-hall",
23
- "8": "cond-mat.mtrl-sci",
24
- "9": "cond-mat.quant-gas",
25
- "10": "cond-mat.soft",
26
- "11": "cond-mat.stat-mech",
27
- "12": "cond-mat.str-el",
28
- "13": "cond-mat.supr-con",
29
- "14": "cs.AI",
30
- "15": "cs.CC",
31
- "16": "cs.CG",
32
- "17": "cs.CL",
33
- "18": "cs.CR",
34
- "19": "cs.CV",
35
- "20": "cs.CY",
36
- "21": "cs.DB",
37
- "22": "cs.DC",
38
- "23": "cs.DM",
39
- "24": "cs.DS",
40
- "25": "cs.GT",
41
- "26": "cs.HC",
42
- "27": "cs.IR",
43
- "28": "cs.IT",
44
- "29": "cs.LG",
45
- "30": "cs.LO",
46
- "31": "cs.NE",
47
- "32": "cs.NI",
48
- "33": "cs.PL",
49
- "34": "cs.RO",
50
- "35": "cs.SD",
51
- "36": "cs.SE",
52
- "37": "cs.SI",
53
- "38": "cs.SY",
54
- "39": "econ.EM",
55
- "40": "econ.GN",
56
- "41": "econ.TH",
57
- "42": "eess.AS",
58
- "43": "eess.IV",
59
- "44": "eess.SP",
60
- "45": "eess.SY",
61
- "46": "gr-qc",
62
- "47": "hep-ex",
63
- "48": "hep-lat",
64
- "49": "hep-ph",
65
- "50": "hep-th",
66
- "51": "math-ph",
67
- "52": "math.AC",
68
- "53": "math.AG",
69
- "54": "math.AP",
70
- "55": "math.AT",
71
- "56": "math.CA",
72
- "57": "math.CO",
73
- "58": "math.CT",
74
- "59": "math.CV",
75
- "60": "math.DG",
76
- "61": "math.DS",
77
- "62": "math.FA",
78
- "63": "math.GM",
79
- "64": "math.GR",
80
- "65": "math.GT",
81
- "66": "math.LO",
82
- "67": "math.MG",
83
- "68": "math.NA",
84
- "69": "math.NT",
85
- "70": "math.OA",
86
- "71": "math.OC",
87
- "72": "math.PR",
88
- "73": "math.QA",
89
- "74": "math.RA",
90
- "75": "math.RT",
91
- "76": "math.SG",
92
- "77": "math.SP",
93
- "78": "math.ST",
94
- "79": "nlin.CD",
95
- "80": "nlin.PS",
96
- "81": "nlin.SI",
97
- "82": "nucl-ex",
98
- "83": "nucl-th",
99
- "84": "physics.acc-ph",
100
- "85": "physics.app-ph",
101
- "86": "physics.atom-ph",
102
- "87": "physics.bio-ph",
103
- "88": "physics.chem-ph",
104
- "89": "physics.class-ph",
105
- "90": "physics.comp-ph",
106
- "91": "physics.flu-dyn",
107
- "92": "physics.gen-ph",
108
- "93": "physics.geo-ph",
109
- "94": "physics.ins-det",
110
- "95": "physics.med-ph",
111
- "96": "physics.optics",
112
- "97": "physics.plasm-ph",
113
- "98": "physics.soc-ph",
114
- "99": "q-bio.BM",
115
- "100": "q-bio.CB",
116
- "101": "q-bio.GN",
117
- "102": "q-bio.MN",
118
- "103": "q-bio.NC",
119
- "104": "q-bio.OT",
120
- "105": "q-bio.PE",
121
- "106": "q-bio.QM",
122
- "107": "q-bio.SC",
123
- "108": "q-bio.TO",
124
- "109": "q-fin.CP",
125
- "110": "q-fin.GN",
126
- "111": "q-fin.MF",
127
- "112": "q-fin.PM",
128
- "113": "q-fin.PR",
129
- "114": "q-fin.RM",
130
- "115": "q-fin.ST",
131
- "116": "q-fin.TR",
132
- "117": "quant-ph",
133
- "118": "stat.AP",
134
- "119": "stat.CO",
135
- "120": "stat.ME",
136
- "121": "stat.ML"
137
- },
138
- "initializer_range": 0.02,
139
- "intermediate_size": 3072,
140
- "is_decoder": false,
141
- "label2id": {
142
- "astro-ph.CO": 0,
143
- "astro-ph.EP": 1,
144
- "astro-ph.GA": 2,
145
- "astro-ph.HE": 3,
146
- "astro-ph.IM": 4,
147
- "astro-ph.SR": 5,
148
- "cond-mat.dis-nn": 6,
149
- "cond-mat.mes-hall": 7,
150
- "cond-mat.mtrl-sci": 8,
151
- "cond-mat.quant-gas": 9,
152
- "cond-mat.soft": 10,
153
- "cond-mat.stat-mech": 11,
154
- "cond-mat.str-el": 12,
155
- "cond-mat.supr-con": 13,
156
- "cs.AI": 14,
157
- "cs.CC": 15,
158
- "cs.CG": 16,
159
- "cs.CL": 17,
160
- "cs.CR": 18,
161
- "cs.CV": 19,
162
- "cs.CY": 20,
163
- "cs.DB": 21,
164
- "cs.DC": 22,
165
- "cs.DM": 23,
166
- "cs.DS": 24,
167
- "cs.GT": 25,
168
- "cs.HC": 26,
169
- "cs.IR": 27,
170
- "cs.IT": 28,
171
- "cs.LG": 29,
172
- "cs.LO": 30,
173
- "cs.NE": 31,
174
- "cs.NI": 32,
175
- "cs.PL": 33,
176
- "cs.RO": 34,
177
- "cs.SD": 35,
178
- "cs.SE": 36,
179
- "cs.SI": 37,
180
- "cs.SY": 38,
181
- "econ.EM": 39,
182
- "econ.GN": 40,
183
- "econ.TH": 41,
184
- "eess.AS": 42,
185
- "eess.IV": 43,
186
- "eess.SP": 44,
187
- "eess.SY": 45,
188
- "gr-qc": 46,
189
- "hep-ex": 47,
190
- "hep-lat": 48,
191
- "hep-ph": 49,
192
- "hep-th": 50,
193
- "math-ph": 51,
194
- "math.AC": 52,
195
- "math.AG": 53,
196
- "math.AP": 54,
197
- "math.AT": 55,
198
- "math.CA": 56,
199
- "math.CO": 57,
200
- "math.CT": 58,
201
- "math.CV": 59,
202
- "math.DG": 60,
203
- "math.DS": 61,
204
- "math.FA": 62,
205
- "math.GM": 63,
206
- "math.GR": 64,
207
- "math.GT": 65,
208
- "math.LO": 66,
209
- "math.MG": 67,
210
- "math.NA": 68,
211
- "math.NT": 69,
212
- "math.OA": 70,
213
- "math.OC": 71,
214
- "math.PR": 72,
215
- "math.QA": 73,
216
- "math.RA": 74,
217
- "math.RT": 75,
218
- "math.SG": 76,
219
- "math.SP": 77,
220
- "math.ST": 78,
221
- "nlin.CD": 79,
222
- "nlin.PS": 80,
223
- "nlin.SI": 81,
224
- "nucl-ex": 82,
225
- "nucl-th": 83,
226
- "physics.acc-ph": 84,
227
- "physics.app-ph": 85,
228
- "physics.atom-ph": 86,
229
- "physics.bio-ph": 87,
230
- "physics.chem-ph": 88,
231
- "physics.class-ph": 89,
232
- "physics.comp-ph": 90,
233
- "physics.flu-dyn": 91,
234
- "physics.gen-ph": 92,
235
- "physics.geo-ph": 93,
236
- "physics.ins-det": 94,
237
- "physics.med-ph": 95,
238
- "physics.optics": 96,
239
- "physics.plasm-ph": 97,
240
- "physics.soc-ph": 98,
241
- "q-bio.BM": 99,
242
- "q-bio.CB": 100,
243
- "q-bio.GN": 101,
244
- "q-bio.MN": 102,
245
- "q-bio.NC": 103,
246
- "q-bio.OT": 104,
247
- "q-bio.PE": 105,
248
- "q-bio.QM": 106,
249
- "q-bio.SC": 107,
250
- "q-bio.TO": 108,
251
- "q-fin.CP": 109,
252
- "q-fin.GN": 110,
253
- "q-fin.MF": 111,
254
- "q-fin.PM": 112,
255
- "q-fin.PR": 113,
256
- "q-fin.RM": 114,
257
- "q-fin.ST": 115,
258
- "q-fin.TR": 116,
259
- "quant-ph": 117,
260
- "stat.AP": 118,
261
- "stat.CO": 119,
262
- "stat.ME": 120,
263
- "stat.ML": 121
264
- },
265
- "layer_norm_eps": 1e-12,
266
- "max_position_embeddings": 512,
267
- "model_type": "bert",
268
- "num_attention_heads": 12,
269
- "num_hidden_layers": 12,
270
- "pad_token_id": 0,
271
- "problem_type": "single_label_classification",
272
- "tie_word_embeddings": true,
273
- "transformers_version": "5.5.0",
274
- "type_vocab_size": 2,
275
- "use_cache": false,
276
- "vocab_size": 31090
277
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model_v2/id2label.json DELETED
@@ -1,124 +0,0 @@
1
- {
2
- "0": "astro-ph.CO",
3
- "1": "astro-ph.EP",
4
- "2": "astro-ph.GA",
5
- "3": "astro-ph.HE",
6
- "4": "astro-ph.IM",
7
- "5": "astro-ph.SR",
8
- "6": "cond-mat.dis-nn",
9
- "7": "cond-mat.mes-hall",
10
- "8": "cond-mat.mtrl-sci",
11
- "9": "cond-mat.quant-gas",
12
- "10": "cond-mat.soft",
13
- "11": "cond-mat.stat-mech",
14
- "12": "cond-mat.str-el",
15
- "13": "cond-mat.supr-con",
16
- "14": "cs.AI",
17
- "15": "cs.CC",
18
- "16": "cs.CG",
19
- "17": "cs.CL",
20
- "18": "cs.CR",
21
- "19": "cs.CV",
22
- "20": "cs.CY",
23
- "21": "cs.DB",
24
- "22": "cs.DC",
25
- "23": "cs.DM",
26
- "24": "cs.DS",
27
- "25": "cs.GT",
28
- "26": "cs.HC",
29
- "27": "cs.IR",
30
- "28": "cs.IT",
31
- "29": "cs.LG",
32
- "30": "cs.LO",
33
- "31": "cs.NE",
34
- "32": "cs.NI",
35
- "33": "cs.PL",
36
- "34": "cs.RO",
37
- "35": "cs.SD",
38
- "36": "cs.SE",
39
- "37": "cs.SI",
40
- "38": "cs.SY",
41
- "39": "econ.EM",
42
- "40": "econ.GN",
43
- "41": "econ.TH",
44
- "42": "eess.AS",
45
- "43": "eess.IV",
46
- "44": "eess.SP",
47
- "45": "eess.SY",
48
- "46": "gr-qc",
49
- "47": "hep-ex",
50
- "48": "hep-lat",
51
- "49": "hep-ph",
52
- "50": "hep-th",
53
- "51": "math-ph",
54
- "52": "math.AC",
55
- "53": "math.AG",
56
- "54": "math.AP",
57
- "55": "math.AT",
58
- "56": "math.CA",
59
- "57": "math.CO",
60
- "58": "math.CT",
61
- "59": "math.CV",
62
- "60": "math.DG",
63
- "61": "math.DS",
64
- "62": "math.FA",
65
- "63": "math.GM",
66
- "64": "math.GR",
67
- "65": "math.GT",
68
- "66": "math.LO",
69
- "67": "math.MG",
70
- "68": "math.NA",
71
- "69": "math.NT",
72
- "70": "math.OA",
73
- "71": "math.OC",
74
- "72": "math.PR",
75
- "73": "math.QA",
76
- "74": "math.RA",
77
- "75": "math.RT",
78
- "76": "math.SG",
79
- "77": "math.SP",
80
- "78": "math.ST",
81
- "79": "nlin.CD",
82
- "80": "nlin.PS",
83
- "81": "nlin.SI",
84
- "82": "nucl-ex",
85
- "83": "nucl-th",
86
- "84": "physics.acc-ph",
87
- "85": "physics.app-ph",
88
- "86": "physics.atom-ph",
89
- "87": "physics.bio-ph",
90
- "88": "physics.chem-ph",
91
- "89": "physics.class-ph",
92
- "90": "physics.comp-ph",
93
- "91": "physics.flu-dyn",
94
- "92": "physics.gen-ph",
95
- "93": "physics.geo-ph",
96
- "94": "physics.ins-det",
97
- "95": "physics.med-ph",
98
- "96": "physics.optics",
99
- "97": "physics.plasm-ph",
100
- "98": "physics.soc-ph",
101
- "99": "q-bio.BM",
102
- "100": "q-bio.CB",
103
- "101": "q-bio.GN",
104
- "102": "q-bio.MN",
105
- "103": "q-bio.NC",
106
- "104": "q-bio.OT",
107
- "105": "q-bio.PE",
108
- "106": "q-bio.QM",
109
- "107": "q-bio.SC",
110
- "108": "q-bio.TO",
111
- "109": "q-fin.CP",
112
- "110": "q-fin.GN",
113
- "111": "q-fin.MF",
114
- "112": "q-fin.PM",
115
- "113": "q-fin.PR",
116
- "114": "q-fin.RM",
117
- "115": "q-fin.ST",
118
- "116": "q-fin.TR",
119
- "117": "quant-ph",
120
- "118": "stat.AP",
121
- "119": "stat.CO",
122
- "120": "stat.ME",
123
- "121": "stat.ML"
124
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model_v2/label2id.json DELETED
@@ -1,124 +0,0 @@
1
- {
2
- "astro-ph.CO": 0,
3
- "astro-ph.EP": 1,
4
- "astro-ph.GA": 2,
5
- "astro-ph.HE": 3,
6
- "astro-ph.IM": 4,
7
- "astro-ph.SR": 5,
8
- "cond-mat.dis-nn": 6,
9
- "cond-mat.mes-hall": 7,
10
- "cond-mat.mtrl-sci": 8,
11
- "cond-mat.quant-gas": 9,
12
- "cond-mat.soft": 10,
13
- "cond-mat.stat-mech": 11,
14
- "cond-mat.str-el": 12,
15
- "cond-mat.supr-con": 13,
16
- "cs.AI": 14,
17
- "cs.CC": 15,
18
- "cs.CG": 16,
19
- "cs.CL": 17,
20
- "cs.CR": 18,
21
- "cs.CV": 19,
22
- "cs.CY": 20,
23
- "cs.DB": 21,
24
- "cs.DC": 22,
25
- "cs.DM": 23,
26
- "cs.DS": 24,
27
- "cs.GT": 25,
28
- "cs.HC": 26,
29
- "cs.IR": 27,
30
- "cs.IT": 28,
31
- "cs.LG": 29,
32
- "cs.LO": 30,
33
- "cs.NE": 31,
34
- "cs.NI": 32,
35
- "cs.PL": 33,
36
- "cs.RO": 34,
37
- "cs.SD": 35,
38
- "cs.SE": 36,
39
- "cs.SI": 37,
40
- "cs.SY": 38,
41
- "econ.EM": 39,
42
- "econ.GN": 40,
43
- "econ.TH": 41,
44
- "eess.AS": 42,
45
- "eess.IV": 43,
46
- "eess.SP": 44,
47
- "eess.SY": 45,
48
- "gr-qc": 46,
49
- "hep-ex": 47,
50
- "hep-lat": 48,
51
- "hep-ph": 49,
52
- "hep-th": 50,
53
- "math-ph": 51,
54
- "math.AC": 52,
55
- "math.AG": 53,
56
- "math.AP": 54,
57
- "math.AT": 55,
58
- "math.CA": 56,
59
- "math.CO": 57,
60
- "math.CT": 58,
61
- "math.CV": 59,
62
- "math.DG": 60,
63
- "math.DS": 61,
64
- "math.FA": 62,
65
- "math.GM": 63,
66
- "math.GR": 64,
67
- "math.GT": 65,
68
- "math.LO": 66,
69
- "math.MG": 67,
70
- "math.NA": 68,
71
- "math.NT": 69,
72
- "math.OA": 70,
73
- "math.OC": 71,
74
- "math.PR": 72,
75
- "math.QA": 73,
76
- "math.RA": 74,
77
- "math.RT": 75,
78
- "math.SG": 76,
79
- "math.SP": 77,
80
- "math.ST": 78,
81
- "nlin.CD": 79,
82
- "nlin.PS": 80,
83
- "nlin.SI": 81,
84
- "nucl-ex": 82,
85
- "nucl-th": 83,
86
- "physics.acc-ph": 84,
87
- "physics.app-ph": 85,
88
- "physics.atom-ph": 86,
89
- "physics.bio-ph": 87,
90
- "physics.chem-ph": 88,
91
- "physics.class-ph": 89,
92
- "physics.comp-ph": 90,
93
- "physics.flu-dyn": 91,
94
- "physics.gen-ph": 92,
95
- "physics.geo-ph": 93,
96
- "physics.ins-det": 94,
97
- "physics.med-ph": 95,
98
- "physics.optics": 96,
99
- "physics.plasm-ph": 97,
100
- "physics.soc-ph": 98,
101
- "q-bio.BM": 99,
102
- "q-bio.CB": 100,
103
- "q-bio.GN": 101,
104
- "q-bio.MN": 102,
105
- "q-bio.NC": 103,
106
- "q-bio.OT": 104,
107
- "q-bio.PE": 105,
108
- "q-bio.QM": 106,
109
- "q-bio.SC": 107,
110
- "q-bio.TO": 108,
111
- "q-fin.CP": 109,
112
- "q-fin.GN": 110,
113
- "q-fin.MF": 111,
114
- "q-fin.PM": 112,
115
- "q-fin.PR": 113,
116
- "q-fin.RM": 114,
117
- "q-fin.ST": 115,
118
- "q-fin.TR": 116,
119
- "quant-ph": 117,
120
- "stat.AP": 118,
121
- "stat.CO": 119,
122
- "stat.ME": 120,
123
- "stat.ML": 121
124
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model_v2/label_full.json DELETED
@@ -1,130 +0,0 @@
1
- {
2
- "cs.AI": "CS: Artificial Intelligence",
3
- "cs.AR": "CS: Hardware Architecture",
4
- "cs.CC": "CS: Computational Complexity",
5
- "cs.CE": "CS: Computational Engineering",
6
- "cs.CG": "CS: Computational Geometry",
7
- "cs.CL": "CS: Computation & Language (NLP)",
8
- "cs.CR": "CS: Cryptography & Security",
9
- "cs.CV": "CS: Computer Vision",
10
- "cs.CY": "CS: Computers & Society",
11
- "cs.DB": "CS: Databases",
12
- "cs.DC": "CS: Distributed & Parallel Computing",
13
- "cs.DM": "CS: Discrete Mathematics",
14
- "cs.DS": "CS: Data Structures & Algorithms",
15
- "cs.GT": "CS: Game Theory",
16
- "cs.HC": "CS: Human-Computer Interaction",
17
- "cs.IR": "CS: Information Retrieval",
18
- "cs.IT": "CS: Information Theory",
19
- "cs.LG": "CS: Machine Learning",
20
- "cs.LO": "CS: Logic in Computer Science",
21
- "cs.NE": "CS: Neural & Evolutionary Computing",
22
- "cs.NI": "CS: Networking & Internet Architecture",
23
- "cs.PL": "CS: Programming Languages",
24
- "cs.RO": "CS: Robotics",
25
- "cs.SD": "CS: Sound",
26
- "cs.SE": "CS: Software Engineering",
27
- "cs.SI": "CS: Social & Information Networks",
28
- "cs.SY": "CS: Systems & Control",
29
- "math.AC": "Math: Commutative Algebra",
30
- "math.AG": "Math: Algebraic Geometry",
31
- "math.AP": "Math: Analysis of PDEs",
32
- "math.AT": "Math: Algebraic Topology",
33
- "math.CA": "Math: Classical Analysis & ODEs",
34
- "math.CO": "Math: Combinatorics",
35
- "math.CT": "Math: Category Theory",
36
- "math.CV": "Math: Complex Variables",
37
- "math.DG": "Math: Differential Geometry",
38
- "math.DS": "Math: Dynamical Systems",
39
- "math.FA": "Math: Functional Analysis",
40
- "math.GM": "Math: General Mathematics",
41
- "math.GR": "Math: Group Theory",
42
- "math.GT": "Math: Geometric Topology",
43
- "math.LO": "Math: Logic",
44
- "math.MG": "Math: Metric Geometry",
45
- "math.NA": "Math: Numerical Analysis",
46
- "math.NT": "Math: Number Theory",
47
- "math.OA": "Math: Operator Algebras",
48
- "math.OC": "Math: Optimization & Control",
49
- "math.PR": "Math: Probability",
50
- "math.QA": "Math: Quantum Algebra",
51
- "math.RA": "Math: Rings & Algebras",
52
- "math.RT": "Math: Representation Theory",
53
- "math.SG": "Math: Symplectic Geometry",
54
- "math.SP": "Math: Spectral Theory",
55
- "math.ST": "Math: Statistics Theory",
56
- "math-ph": "Mathematical Physics",
57
- "quant-ph": "Physics: Quantum Physics",
58
- "gr-qc": "Physics: General Relativity & Quantum Cosmology",
59
- "hep-ph": "Physics: High Energy (Phenomenology)",
60
- "hep-th": "Physics: High Energy (Theory)",
61
- "hep-ex": "Physics: High Energy (Experiment)",
62
- "hep-lat": "Physics: High Energy (Lattice)",
63
- "nucl-th": "Physics: Nuclear Theory",
64
- "nucl-ex": "Physics: Nuclear Experiment",
65
- "physics.acc-ph": "Physics: Accelerator",
66
- "physics.app-ph": "Physics: Applied Physics",
67
- "physics.atom-ph": "Physics: Atomic Physics",
68
- "physics.bio-ph": "Physics: Biological Physics",
69
- "physics.chem-ph": "Physics: Chemical Physics",
70
- "physics.class-ph": "Physics: Classical Physics",
71
- "physics.comp-ph": "Physics: Computational Physics",
72
- "physics.flu-dyn": "Physics: Fluid Dynamics",
73
- "physics.gen-ph": "Physics: General Physics",
74
- "physics.geo-ph": "Physics: Geophysics",
75
- "physics.ins-det": "Physics: Instrumentation & Detectors",
76
- "physics.med-ph": "Physics: Medical Physics",
77
- "physics.optics": "Physics: Optics",
78
- "physics.plasm-ph": "Physics: Plasma Physics",
79
- "physics.soc-ph": "Physics: Physics & Society",
80
- "physics.space-ph": "Physics: Space Physics",
81
- "astro-ph.CO": "Astrophysics: Cosmology",
82
- "astro-ph.EP": "Astrophysics: Earth & Planetary",
83
- "astro-ph.GA": "Astrophysics: Galaxies",
84
- "astro-ph.HE": "Astrophysics: High Energy",
85
- "astro-ph.IM": "Astrophysics: Instrumentation",
86
- "astro-ph.SR": "Astrophysics: Solar & Stellar",
87
- "cond-mat.dis-nn": "Cond-Mat: Disordered Systems",
88
- "cond-mat.mes-hall": "Cond-Mat: Mesoscale & Nanoscale",
89
- "cond-mat.mtrl-sci": "Cond-Mat: Materials Science",
90
- "cond-mat.quant-gas": "Cond-Mat: Quantum Gases",
91
- "cond-mat.soft": "Cond-Mat: Soft Matter",
92
- "cond-mat.stat-mech": "Cond-Mat: Statistical Mechanics",
93
- "cond-mat.str-el": "Cond-Mat: Strongly Correlated Electrons",
94
- "cond-mat.supr-con": "Cond-Mat: Superconductivity",
95
- "stat.AP": "Statistics: Applications",
96
- "stat.CO": "Statistics: Computation",
97
- "stat.ME": "Statistics: Methodology",
98
- "stat.ML": "Statistics: Machine Learning",
99
- "stat.OT": "Statistics: Other",
100
- "stat.TH": "Statistics: Theory",
101
- "eess.AS": "EESS: Audio & Speech",
102
- "eess.IV": "EESS: Image & Video Processing",
103
- "eess.SP": "EESS: Signal Processing",
104
- "eess.SY": "EESS: Systems & Control",
105
- "q-bio.BM": "Q-Bio: Biomolecules",
106
- "q-bio.CB": "Q-Bio: Cell Behavior",
107
- "q-bio.GN": "Q-Bio: Genomics",
108
- "q-bio.MN": "Q-Bio: Molecular Networks",
109
- "q-bio.NC": "Q-Bio: Neurons & Cognition",
110
- "q-bio.OT": "Q-Bio: Other",
111
- "q-bio.PE": "Q-Bio: Populations & Evolution",
112
- "q-bio.QM": "Q-Bio: Quantitative Methods",
113
- "q-bio.SC": "Q-Bio: Subcellular Processes",
114
- "q-bio.TO": "Q-Bio: Tissues & Organs",
115
- "q-fin.CP": "Q-Fin: Computational Finance",
116
- "q-fin.EC": "Q-Fin: Economics",
117
- "q-fin.GN": "Q-Fin: General Finance",
118
- "q-fin.MF": "Q-Fin: Mathematical Finance",
119
- "q-fin.PM": "Q-Fin: Portfolio Management",
120
- "q-fin.PR": "Q-Fin: Pricing of Securities",
121
- "q-fin.RM": "Q-Fin: Risk Management",
122
- "q-fin.ST": "Q-Fin: Statistical Finance",
123
- "q-fin.TR": "Q-Fin: Trading & Market Microstructure",
124
- "econ.EM": "Econ: Econometrics",
125
- "econ.GN": "Econ: General Economics",
126
- "econ.TH": "Econ: Theoretical Economics",
127
- "nlin.CD": "Nonlin: Chaotic Dynamics",
128
- "nlin.PS": "Nonlin: Pattern Formation & Solitons",
129
- "nlin.SI": "Nonlin: Exactly Solvable & Integrable Systems"
130
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model_v2/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2972a8f3ef090222a7ab37e34b5819fe47b6d9de25fc2be989036282f2db0c0b
3
- size 191623496
 
 
 
 
src/model_v2/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7b0e8d382ed5827481502deca3ccc4a5397e47ab0309b845e7266ad6e520cf0
3
- size 198473472
 
 
 
 
src/model_v2/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a735ecf16212850fdfe2e144b276e3b730114bebe172be703762d651f5cc9e0
3
- size 49975528
 
 
 
 
src/model_v2/model.safetensors.index.json DELETED
@@ -1,209 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 110012282,
4
- "total_size": 440049128
5
- },
6
- "weight_map": {
7
- "bert.embeddings.LayerNorm.beta": "model-00001-of-00003.safetensors",
8
- "bert.embeddings.LayerNorm.gamma": "model-00001-of-00003.safetensors",
9
- "bert.embeddings.position_embeddings.weight": "model-00001-of-00003.safetensors",
10
- "bert.embeddings.token_type_embeddings.weight": "model-00001-of-00003.safetensors",
11
- "bert.embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
12
- "bert.encoder.layer.0.attention.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
13
- "bert.encoder.layer.0.attention.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
14
- "bert.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
15
- "bert.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
16
- "bert.encoder.layer.0.attention.self.key.bias": "model-00001-of-00003.safetensors",
17
- "bert.encoder.layer.0.attention.self.key.weight": "model-00001-of-00003.safetensors",
18
- "bert.encoder.layer.0.attention.self.query.bias": "model-00001-of-00003.safetensors",
19
- "bert.encoder.layer.0.attention.self.query.weight": "model-00001-of-00003.safetensors",
20
- "bert.encoder.layer.0.attention.self.value.bias": "model-00001-of-00003.safetensors",
21
- "bert.encoder.layer.0.attention.self.value.weight": "model-00001-of-00003.safetensors",
22
- "bert.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors",
23
- "bert.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors",
24
- "bert.encoder.layer.0.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
25
- "bert.encoder.layer.0.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
26
- "bert.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors",
27
- "bert.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors",
28
- "bert.encoder.layer.1.attention.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
29
- "bert.encoder.layer.1.attention.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
30
- "bert.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
31
- "bert.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
32
- "bert.encoder.layer.1.attention.self.key.bias": "model-00001-of-00003.safetensors",
33
- "bert.encoder.layer.1.attention.self.key.weight": "model-00001-of-00003.safetensors",
34
- "bert.encoder.layer.1.attention.self.query.bias": "model-00001-of-00003.safetensors",
35
- "bert.encoder.layer.1.attention.self.query.weight": "model-00001-of-00003.safetensors",
36
- "bert.encoder.layer.1.attention.self.value.bias": "model-00001-of-00003.safetensors",
37
- "bert.encoder.layer.1.attention.self.value.weight": "model-00001-of-00003.safetensors",
38
- "bert.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors",
39
- "bert.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors",
40
- "bert.encoder.layer.1.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
41
- "bert.encoder.layer.1.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
42
- "bert.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors",
43
- "bert.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors",
44
- "bert.encoder.layer.10.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
45
- "bert.encoder.layer.10.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
46
- "bert.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00003.safetensors",
47
- "bert.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00003.safetensors",
48
- "bert.encoder.layer.10.attention.self.key.bias": "model-00002-of-00003.safetensors",
49
- "bert.encoder.layer.10.attention.self.key.weight": "model-00002-of-00003.safetensors",
50
- "bert.encoder.layer.10.attention.self.query.bias": "model-00002-of-00003.safetensors",
51
- "bert.encoder.layer.10.attention.self.query.weight": "model-00002-of-00003.safetensors",
52
- "bert.encoder.layer.10.attention.self.value.bias": "model-00002-of-00003.safetensors",
53
- "bert.encoder.layer.10.attention.self.value.weight": "model-00002-of-00003.safetensors",
54
- "bert.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00003.safetensors",
55
- "bert.encoder.layer.10.intermediate.dense.weight": "model-00003-of-00003.safetensors",
56
- "bert.encoder.layer.10.output.LayerNorm.beta": "model-00003-of-00003.safetensors",
57
- "bert.encoder.layer.10.output.LayerNorm.gamma": "model-00003-of-00003.safetensors",
58
- "bert.encoder.layer.10.output.dense.bias": "model-00003-of-00003.safetensors",
59
- "bert.encoder.layer.10.output.dense.weight": "model-00003-of-00003.safetensors",
60
- "bert.encoder.layer.11.attention.output.LayerNorm.beta": "model-00003-of-00003.safetensors",
61
- "bert.encoder.layer.11.attention.output.LayerNorm.gamma": "model-00003-of-00003.safetensors",
62
- "bert.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00003.safetensors",
63
- "bert.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00003.safetensors",
64
- "bert.encoder.layer.11.attention.self.key.bias": "model-00003-of-00003.safetensors",
65
- "bert.encoder.layer.11.attention.self.key.weight": "model-00003-of-00003.safetensors",
66
- "bert.encoder.layer.11.attention.self.query.bias": "model-00003-of-00003.safetensors",
67
- "bert.encoder.layer.11.attention.self.query.weight": "model-00003-of-00003.safetensors",
68
- "bert.encoder.layer.11.attention.self.value.bias": "model-00003-of-00003.safetensors",
69
- "bert.encoder.layer.11.attention.self.value.weight": "model-00003-of-00003.safetensors",
70
- "bert.encoder.layer.11.intermediate.dense.bias": "model-00003-of-00003.safetensors",
71
- "bert.encoder.layer.11.intermediate.dense.weight": "model-00003-of-00003.safetensors",
72
- "bert.encoder.layer.11.output.LayerNorm.beta": "model-00003-of-00003.safetensors",
73
- "bert.encoder.layer.11.output.LayerNorm.gamma": "model-00003-of-00003.safetensors",
74
- "bert.encoder.layer.11.output.dense.bias": "model-00003-of-00003.safetensors",
75
- "bert.encoder.layer.11.output.dense.weight": "model-00003-of-00003.safetensors",
76
- "bert.encoder.layer.2.attention.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
77
- "bert.encoder.layer.2.attention.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
78
- "bert.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
79
- "bert.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
80
- "bert.encoder.layer.2.attention.self.key.bias": "model-00001-of-00003.safetensors",
81
- "bert.encoder.layer.2.attention.self.key.weight": "model-00001-of-00003.safetensors",
82
- "bert.encoder.layer.2.attention.self.query.bias": "model-00001-of-00003.safetensors",
83
- "bert.encoder.layer.2.attention.self.query.weight": "model-00001-of-00003.safetensors",
84
- "bert.encoder.layer.2.attention.self.value.bias": "model-00001-of-00003.safetensors",
85
- "bert.encoder.layer.2.attention.self.value.weight": "model-00001-of-00003.safetensors",
86
- "bert.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors",
87
- "bert.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors",
88
- "bert.encoder.layer.2.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
89
- "bert.encoder.layer.2.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
90
- "bert.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors",
91
- "bert.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors",
92
- "bert.encoder.layer.3.attention.output.LayerNorm.beta": "model-00001-of-00003.safetensors",
93
- "bert.encoder.layer.3.attention.output.LayerNorm.gamma": "model-00001-of-00003.safetensors",
94
- "bert.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
95
- "bert.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
96
- "bert.encoder.layer.3.attention.self.key.bias": "model-00001-of-00003.safetensors",
97
- "bert.encoder.layer.3.attention.self.key.weight": "model-00001-of-00003.safetensors",
98
- "bert.encoder.layer.3.attention.self.query.bias": "model-00001-of-00003.safetensors",
99
- "bert.encoder.layer.3.attention.self.query.weight": "model-00001-of-00003.safetensors",
100
- "bert.encoder.layer.3.attention.self.value.bias": "model-00001-of-00003.safetensors",
101
- "bert.encoder.layer.3.attention.self.value.weight": "model-00001-of-00003.safetensors",
102
- "bert.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors",
103
- "bert.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00003.safetensors",
104
- "bert.encoder.layer.3.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
105
- "bert.encoder.layer.3.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
106
- "bert.encoder.layer.3.output.dense.bias": "model-00002-of-00003.safetensors",
107
- "bert.encoder.layer.3.output.dense.weight": "model-00002-of-00003.safetensors",
108
- "bert.encoder.layer.4.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
109
- "bert.encoder.layer.4.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
110
- "bert.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00003.safetensors",
111
- "bert.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00003.safetensors",
112
- "bert.encoder.layer.4.attention.self.key.bias": "model-00002-of-00003.safetensors",
113
- "bert.encoder.layer.4.attention.self.key.weight": "model-00002-of-00003.safetensors",
114
- "bert.encoder.layer.4.attention.self.query.bias": "model-00002-of-00003.safetensors",
115
- "bert.encoder.layer.4.attention.self.query.weight": "model-00002-of-00003.safetensors",
116
- "bert.encoder.layer.4.attention.self.value.bias": "model-00002-of-00003.safetensors",
117
- "bert.encoder.layer.4.attention.self.value.weight": "model-00002-of-00003.safetensors",
118
- "bert.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00003.safetensors",
119
- "bert.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00003.safetensors",
120
- "bert.encoder.layer.4.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
121
- "bert.encoder.layer.4.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
122
- "bert.encoder.layer.4.output.dense.bias": "model-00002-of-00003.safetensors",
123
- "bert.encoder.layer.4.output.dense.weight": "model-00002-of-00003.safetensors",
124
- "bert.encoder.layer.5.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
125
- "bert.encoder.layer.5.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
126
- "bert.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00003.safetensors",
127
- "bert.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00003.safetensors",
128
- "bert.encoder.layer.5.attention.self.key.bias": "model-00002-of-00003.safetensors",
129
- "bert.encoder.layer.5.attention.self.key.weight": "model-00002-of-00003.safetensors",
130
- "bert.encoder.layer.5.attention.self.query.bias": "model-00002-of-00003.safetensors",
131
- "bert.encoder.layer.5.attention.self.query.weight": "model-00002-of-00003.safetensors",
132
- "bert.encoder.layer.5.attention.self.value.bias": "model-00002-of-00003.safetensors",
133
- "bert.encoder.layer.5.attention.self.value.weight": "model-00002-of-00003.safetensors",
134
- "bert.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00003.safetensors",
135
- "bert.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00003.safetensors",
136
- "bert.encoder.layer.5.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
137
- "bert.encoder.layer.5.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
138
- "bert.encoder.layer.5.output.dense.bias": "model-00002-of-00003.safetensors",
139
- "bert.encoder.layer.5.output.dense.weight": "model-00002-of-00003.safetensors",
140
- "bert.encoder.layer.6.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
141
- "bert.encoder.layer.6.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
142
- "bert.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00003.safetensors",
143
- "bert.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00003.safetensors",
144
- "bert.encoder.layer.6.attention.self.key.bias": "model-00002-of-00003.safetensors",
145
- "bert.encoder.layer.6.attention.self.key.weight": "model-00002-of-00003.safetensors",
146
- "bert.encoder.layer.6.attention.self.query.bias": "model-00002-of-00003.safetensors",
147
- "bert.encoder.layer.6.attention.self.query.weight": "model-00002-of-00003.safetensors",
148
- "bert.encoder.layer.6.attention.self.value.bias": "model-00002-of-00003.safetensors",
149
- "bert.encoder.layer.6.attention.self.value.weight": "model-00002-of-00003.safetensors",
150
- "bert.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00003.safetensors",
151
- "bert.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00003.safetensors",
152
- "bert.encoder.layer.6.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
153
- "bert.encoder.layer.6.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
154
- "bert.encoder.layer.6.output.dense.bias": "model-00002-of-00003.safetensors",
155
- "bert.encoder.layer.6.output.dense.weight": "model-00002-of-00003.safetensors",
156
- "bert.encoder.layer.7.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
157
- "bert.encoder.layer.7.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
158
- "bert.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00003.safetensors",
159
- "bert.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00003.safetensors",
160
- "bert.encoder.layer.7.attention.self.key.bias": "model-00002-of-00003.safetensors",
161
- "bert.encoder.layer.7.attention.self.key.weight": "model-00002-of-00003.safetensors",
162
- "bert.encoder.layer.7.attention.self.query.bias": "model-00002-of-00003.safetensors",
163
- "bert.encoder.layer.7.attention.self.query.weight": "model-00002-of-00003.safetensors",
164
- "bert.encoder.layer.7.attention.self.value.bias": "model-00002-of-00003.safetensors",
165
- "bert.encoder.layer.7.attention.self.value.weight": "model-00002-of-00003.safetensors",
166
- "bert.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00003.safetensors",
167
- "bert.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00003.safetensors",
168
- "bert.encoder.layer.7.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
169
- "bert.encoder.layer.7.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
170
- "bert.encoder.layer.7.output.dense.bias": "model-00002-of-00003.safetensors",
171
- "bert.encoder.layer.7.output.dense.weight": "model-00002-of-00003.safetensors",
172
- "bert.encoder.layer.8.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
173
- "bert.encoder.layer.8.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
174
- "bert.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00003.safetensors",
175
- "bert.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00003.safetensors",
176
- "bert.encoder.layer.8.attention.self.key.bias": "model-00002-of-00003.safetensors",
177
- "bert.encoder.layer.8.attention.self.key.weight": "model-00002-of-00003.safetensors",
178
- "bert.encoder.layer.8.attention.self.query.bias": "model-00002-of-00003.safetensors",
179
- "bert.encoder.layer.8.attention.self.query.weight": "model-00002-of-00003.safetensors",
180
- "bert.encoder.layer.8.attention.self.value.bias": "model-00002-of-00003.safetensors",
181
- "bert.encoder.layer.8.attention.self.value.weight": "model-00002-of-00003.safetensors",
182
- "bert.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00003.safetensors",
183
- "bert.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00003.safetensors",
184
- "bert.encoder.layer.8.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
185
- "bert.encoder.layer.8.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
186
- "bert.encoder.layer.8.output.dense.bias": "model-00002-of-00003.safetensors",
187
- "bert.encoder.layer.8.output.dense.weight": "model-00002-of-00003.safetensors",
188
- "bert.encoder.layer.9.attention.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
189
- "bert.encoder.layer.9.attention.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
190
- "bert.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00003.safetensors",
191
- "bert.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00003.safetensors",
192
- "bert.encoder.layer.9.attention.self.key.bias": "model-00002-of-00003.safetensors",
193
- "bert.encoder.layer.9.attention.self.key.weight": "model-00002-of-00003.safetensors",
194
- "bert.encoder.layer.9.attention.self.query.bias": "model-00002-of-00003.safetensors",
195
- "bert.encoder.layer.9.attention.self.query.weight": "model-00002-of-00003.safetensors",
196
- "bert.encoder.layer.9.attention.self.value.bias": "model-00002-of-00003.safetensors",
197
- "bert.encoder.layer.9.attention.self.value.weight": "model-00002-of-00003.safetensors",
198
- "bert.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00003.safetensors",
199
- "bert.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00003.safetensors",
200
- "bert.encoder.layer.9.output.LayerNorm.beta": "model-00002-of-00003.safetensors",
201
- "bert.encoder.layer.9.output.LayerNorm.gamma": "model-00002-of-00003.safetensors",
202
- "bert.encoder.layer.9.output.dense.bias": "model-00002-of-00003.safetensors",
203
- "bert.encoder.layer.9.output.dense.weight": "model-00002-of-00003.safetensors",
204
- "bert.pooler.dense.bias": "model-00003-of-00003.safetensors",
205
- "bert.pooler.dense.weight": "model-00003-of-00003.safetensors",
206
- "classifier.bias": "model-00003-of-00003.safetensors",
207
- "classifier.weight": "model-00003-of-00003.safetensors"
208
- }
209
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/model_v2/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
src/model_v2/tokenizer_config.json DELETED
@@ -1,21 +0,0 @@
1
- {
2
- "backend": "tokenizers",
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "is_local": true,
6
- "mask_token": "[MASK]",
7
- "max_length": 256,
8
- "model_max_length": 1000000000000000019884624838656,
9
- "pad_to_multiple_of": null,
10
- "pad_token": "[PAD]",
11
- "pad_token_type_id": 0,
12
- "padding_side": "right",
13
- "sep_token": "[SEP]",
14
- "stride": 0,
15
- "strip_accents": null,
16
- "tokenize_chinese_chars": true,
17
- "tokenizer_class": "BertTokenizer",
18
- "truncation_side": "right",
19
- "truncation_strategy": "longest_first",
20
- "unk_token": "[UNK]"
21
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
src/streamlit_app.py CHANGED
@@ -1,334 +1,40 @@
1
- """
2
- arXiv Article Classifier — Streamlit UI
3
-
4
- Запуск локально:
5
- streamlit run app.py --server.port 8080
6
- """
7
-
8
- import json
9
- import os
10
  import numpy as np
 
11
  import streamlit as st
12
- import torch
13
- from transformers import AutoTokenizer, AutoModelForSequenceClassification
14
-
15
- # ---------------------------------------------------------------------------
16
- # Стили
17
- # ---------------------------------------------------------------------------
18
- st.markdown("""
19
- <style>
20
- /* Фон */
21
- .stApp { background-color: #f7faf7; }
22
- .main .block-container { padding-top: 2rem; }
23
-
24
- /* Заголовки */
25
- h1 { color: #2d6a4f !important; letter-spacing: -0.5px; }
26
- h2, h3 { color: #40916c !important; }
27
-
28
- /* Текст */
29
- p, label, .stMarkdown { color: #374151 !important; }
30
-
31
- /* Radio */
32
- .stRadio > label { color: #40916c !important; font-weight: 600; }
33
-
34
- /* Поля ввода */
35
- .stTextInput input, .stTextArea textarea {
36
- background-color: #ffffff !important;
37
- border: 1px solid #b7e4c7 !important;
38
- color: #1f2937 !important;
39
- border-radius: 8px !important;
40
- }
41
- .stTextInput input:focus, .stTextArea textarea:focus {
42
- border-color: #52b788 !important;
43
- box-shadow: 0 0 0 2px rgba(82,183,136,0.15) !important;
44
- }
45
- .stTextInput label, .stTextArea label {
46
- color: #40916c !important;
47
- font-weight: 600;
48
- }
49
-
50
- /* Кнопка */
51
- .stButton > button {
52
- background-color: #52b788 !important;
53
- color: #ffffff !important;
54
- border: none !important;
55
- border-radius: 8px !important;
56
- font-weight: 600;
57
- transition: all 0.2s;
58
- }
59
- .stButton > button:hover {
60
- background-color: #40916c !important;
61
- color: #ffffff !important;
62
- }
63
-
64
- /* Divider */
65
- hr { border-color: #d8f3dc !important; }
66
-
67
- /* Success/error */
68
- .stSuccess { background-color: #d8f3dc !important; color: #1b4332 !important; border-color: #95d5b2 !important; }
69
- .stError { background-color: #fef2f2 !important; }
70
-
71
- /* Sidebar */
72
- [data-testid="stSidebar"] {
73
- background-color: #f0faf2 !important;
74
- border-right: 1px solid #d8f3dc;
75
- }
76
- [data-testid="stSidebar"] p,
77
- [data-testid="stSidebar"] span,
78
- [data-testid="stSidebar"] div { color: #374151 !important; }
79
- [data-testid="stSidebar"] a { color: #40916c !important; }
80
-
81
- /* Карточка категории */
82
- .cat-card {
83
- background: #ffffff;
84
- border: 1px solid #d8f3dc;
85
- border-left: 4px solid #52b788;
86
- border-radius: 8px;
87
- padding: 10px 14px;
88
- margin-bottom: 8px;
89
- }
90
- .cat-title { color: #1b4332; font-weight: 600; font-size: 0.95rem; }
91
- .cat-code { color: #74c69d; font-size: 0.78rem; font-family: monospace; margin-top: 2px; }
92
- .cat-pct { color: #40916c; font-size: 1.2rem; font-weight: 700; float: right; }
93
-
94
- /* Заголовок колонки сравнения */
95
- .col-header {
96
- background: #d8f3dc;
97
- border-radius: 8px;
98
- padding: 8px 14px;
99
- margin-bottom: 12px;
100
- color: #1b4332 !important;
101
- font-weight: 700;
102
- font-size: 0.9rem;
103
- text-align: center;
104
- }
105
- </style>
106
- """, unsafe_allow_html=True)
107
-
108
- # ---------------------------------------------------------------------------
109
- # Конфиг моделей
110
- # ---------------------------------------------------------------------------
111
- MODELS = {
112
- "large": {
113
- "label": "Большая",
114
- "dir": "./src/model_v2",
115
- "base": "allenai/scibert_scivocab_uncased",
116
- "base_url": "https://huggingface.co/allenai/scibert_scivocab_uncased",
117
- "dataset": "mteb/arxiv-clustering-p2p",
118
- "dataset_url": "https://huggingface.co/datasets/mteb/arxiv-clustering-p2p",
119
- "n_classes": 122,
120
- "desc": "SciBERT · 122 категории",
121
- "topics": "CS · Math · Physics · HEP · Astrophysics · Condensed Matter · Statistics · EESS · Quantitative Biology · Quantitative Finance · Economics · Nonlinear Sciences",
122
- },
123
- "small": {
124
- "label": "Простая",
125
- "dir": "./src/model",
126
- "base": "distilbert-base-cased",
127
- "base_url": "https://huggingface.co/distilbert-base-cased",
128
- "dataset": "ccdv/arxiv-classification",
129
- "dataset_url": "https://huggingface.co/datasets/ccdv/arxiv-classification",
130
- "n_classes": 11,
131
- "desc": "DistilBERT · 11 категорий",
132
- "topics": "cs.CV · cs.AI · cs.NE · cs.IT · cs.DS · cs.SY · cs.CE · cs.PL · math.AC · math.GR · math.ST",
133
- },
134
- }
135
-
136
- MAX_LEN = 256
137
- THRESHOLD = 0.95
138
-
139
-
140
- # ---------------------------------------------------------------------------
141
- # Загрузка модели
142
- # ---------------------------------------------------------------------------
143
- @st.cache_resource
144
- def load_model(model_dir: str):
145
- device = (
146
- "mps" if torch.backends.mps.is_available() else
147
- "cuda" if torch.cuda.is_available() else
148
- "cpu"
149
- )
150
- tokenizer = AutoTokenizer.from_pretrained(model_dir)
151
- model = AutoModelForSequenceClassification.from_pretrained(model_dir)
152
- model.to(device)
153
- model.eval()
154
-
155
- with open(f"{model_dir}/id2label.json") as f:
156
- id2label = {int(k): v for k, v in json.load(f).items()}
157
-
158
- label_full = {}
159
- if os.path.exists(f"{model_dir}/label_full.json"):
160
- with open(f"{model_dir}/label_full.json") as f:
161
- label_full = json.load(f)
162
-
163
- return tokenizer, model, id2label, label_full, device
164
-
165
-
166
- def predict_top95(title, abstract, model_dir):
167
- tokenizer, model, id2label, label_full, device = load_model(model_dir)
168
- text = title.strip()
169
- if abstract.strip():
170
- text = text + "\n\n" + abstract.strip()
171
 
172
- enc = tokenizer(
173
- text, max_length=MAX_LEN, padding="max_length",
174
- truncation=True, return_tensors="pt",
175
- ).to(device)
176
-
177
- with torch.no_grad():
178
- logits = model(**enc).logits
179
-
180
- probs = torch.softmax(logits, dim=-1).squeeze().cpu().numpy()
181
- sorted_idx = np.argsort(probs)[::-1]
182
-
183
- result, cumsum = [], 0.0
184
- for idx in sorted_idx:
185
- prob = float(probs[idx])
186
- cat = id2label[int(idx)]
187
- result.append({
188
- "category": cat,
189
- "full_name": label_full.get(cat, cat),
190
- "probability": prob,
191
- })
192
- cumsum += prob
193
- if cumsum >= THRESHOLD:
194
- break
195
- return result
196
-
197
-
198
- def render_results(results):
199
- for rank, r in enumerate(results, start=1):
200
- pct = r["probability"] * 100
201
- bar = int(r["probability"] * 20) * "█" + (20 - int(r["probability"] * 20)) * "░"
202
- st.markdown(f"""
203
- <div class="cat-card">
204
- <span class="cat-pct">{pct:.1f}%</span>
205
- <div class="cat-title">{rank}. {r['full_name']}</div>
206
- <div class="cat-code">{r['category']}</div>
207
- <div style="color:#95d5b2;font-size:0.75rem;letter-spacing:1px;margin-top:4px">{bar}</div>
208
- </div>
209
- """, unsafe_allow_html=True)
210
-
211
-
212
- # ---------------------------------------------------------------------------
213
- # UI
214
- # ---------------------------------------------------------------------------
215
- st.set_page_config(page_title="arXiv Classifier")
216
-
217
- st.markdown("# arXiv Classifier")
218
- st.markdown("<p style='color:#52b788;margin-top:-12px;margin-bottom:8px'>Классификация научных статей по тематике arxiv</p>", unsafe_allow_html=True)
219
-
220
- # Проверяем доступность моделей
221
- available = {k: v for k, v in MODELS.items() if os.path.exists(f"{v['dir']}/config.json")}
222
- if not available:
223
- st.error("Модели не найдены. Сначала запустите обучение.")
224
- st.stop()
225
-
226
- # ---------------------------------------------------------------------------
227
- # Режим работы
228
- # ---------------------------------------------------------------------------
229
- mode = st.radio(
230
- "Режим",
231
- ["Одна модель", "Сравнение моделей"],
232
- horizontal=True,
233
- label_visibility="collapsed",
234
- )
235
-
236
- # ---------------------------------------------------------------------------
237
- # Поля ввода
238
- # ---------------------------------------------------------------------------
239
- title = st.text_input("Название статьи *", placeholder="Например: Attention Is All You Need")
240
- abstract = st.text_area(
241
- "Аннотация (abstract)",
242
- placeholder="Необязательно. Если не указана — классификация только по названию.",
243
- height=150,
244
- )
245
-
246
- # Выбор модели (только в режиме одной)
247
- if mode == "Одна модель":
248
- model_key = st.radio(
249
- "Модель",
250
- list(available.keys()),
251
- format_func=lambda k: f"{available[k]['label']} — {available[k]['desc']}",
252
- horizontal=True,
253
- )
254
- cfg = available[model_key]
255
-
256
- st.divider()
257
- run = st.button("Классифицировать", type="primary", use_container_width=True)
258
-
259
- # ---------------------------------------------------------------------------
260
- # Предсказание
261
- # ---------------------------------------------------------------------------
262
- if run:
263
- if not title.strip():
264
- st.error("Пожалуйста, введите название статьи.")
265
- st.stop()
266
-
267
- if mode == "Одна модель":
268
- cfg = available[model_key]
269
- with st.spinner("Предсказываем..."):
270
- try:
271
- results = predict_top95(title, abstract, cfg["dir"])
272
- except Exception as e:
273
- st.error(f"Ошибка: {e}"); st.stop()
274
-
275
- st.success(f"Топ-{len(results)} категорий (суммарная вероятно��ть ≥ 95%)")
276
- render_results(results)
277
-
278
- else: # Сравнение
279
- if len(available) < 2:
280
- st.warning("Для сравнения нужны обе модели. Сейчас доступна только одна.")
281
- st.stop()
282
-
283
- with st.spinner("Запускаем обе модели..."):
284
- try:
285
- res_large = predict_top95(title, abstract, MODELS["large"]["dir"])
286
- res_small = predict_top95(title, abstract, MODELS["small"]["dir"])
287
- except Exception as e:
288
- st.error(f"Ошибка: {e}"); st.stop()
289
-
290
- col_l, col_r = st.columns(2)
291
-
292
- with col_l:
293
- st.markdown(
294
- f"<div class='col-header'>{MODELS['large']['label']} — {MODELS['large']['desc']}</div>",
295
- unsafe_allow_html=True,
296
- )
297
- render_results(res_large)
298
-
299
- with col_r:
300
- st.markdown(
301
- f"<div class='col-header'>{MODELS['small']['label']} — {MODELS['small']['desc']}</div>",
302
- unsafe_allow_html=True,
303
- )
304
- render_results(res_small)
305
 
306
- # ---------------------------------------------------------------------------
307
- # Сайдбар
308
- # ---------------------------------------------------------------------------
309
- with st.sidebar:
310
- st.markdown("### О сервисе")
311
 
312
- for key, cfg in available.items():
313
- st.markdown(
314
- f"**{cfg['label']}** \n"
315
- f"Модель: [{cfg['base']}]({cfg['base_url']}) \n"
316
- f"Датасет: [{cfg['dataset']}]({cfg['dataset_url']}) \n"
317
- f"Классов: **{cfg['n_classes']}**"
318
- )
319
- # Тематики в виде тегов
320
- tags = cfg["topics"].split(" · ")
321
- tags_html = " ".join(
322
- f"<span style='display:inline-block;background:#d8f3dc;color:#1b4332;"
323
- f"border-radius:4px;padding:1px 6px;font-size:0.72rem;"
324
- f"margin:2px 2px 2px 0;font-family:monospace'>{t}</span>"
325
- for t in tags
326
- )
327
- st.markdown(tags_html, unsafe_allow_html=True)
328
- st.markdown("")
329
 
330
- st.divider()
331
- st.caption(
332
- "**Top-95%** — категории выводятся по убыванию вероятности, "
333
- "пока суммарная вероятность не превысит 95%."
334
- )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import altair as alt
 
 
 
 
 
 
 
 
2
  import numpy as np
3
+ import pandas as pd
4
  import streamlit as st
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
+ """
7
+ # Welcome to Streamlit!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
 
9
+ Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
10
+ If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
11
+ forums](https://discuss.streamlit.io).
 
 
12
 
13
+ In the meantime, below is an example of what you can do with just a few lines of code:
14
+ """
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
 
16
+ num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
17
+ num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
18
+
19
+ indices = np.linspace(0, 1, num_points)
20
+ theta = 2 * np.pi * num_turns * indices
21
+ radius = indices
22
+
23
+ x = radius * np.cos(theta)
24
+ y = radius * np.sin(theta)
25
+
26
+ df = pd.DataFrame({
27
+ "x": x,
28
+ "y": y,
29
+ "idx": indices,
30
+ "rand": np.random.randn(num_points),
31
+ })
32
+
33
+ st.altair_chart(alt.Chart(df, height=700, width=700)
34
+ .mark_point(filled=True)
35
+ .encode(
36
+ x=alt.X("x", axis=None),
37
+ y=alt.Y("y", axis=None),
38
+ color=alt.Color("idx", legend=None, scale=alt.Scale()),
39
+ size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
40
+ ))