Upload folder using huggingface_hub
Browse files- config.json +265 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LongformerForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_mode": "longformer",
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_window": [
|
8 |
+
512,
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"bos_token_id": 0,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"gradient_checkpointing": false,
|
24 |
+
"hidden_act": "gelu",
|
25 |
+
"hidden_dropout_prob": 0.1,
|
26 |
+
"hidden_size": 768,
|
27 |
+
"id2label": {
|
28 |
+
"0": 28,
|
29 |
+
"1": 97,
|
30 |
+
"2": 117,
|
31 |
+
"3": 177,
|
32 |
+
"4": 186,
|
33 |
+
"5": 187,
|
34 |
+
"6": 219,
|
35 |
+
"7": 282,
|
36 |
+
"8": 289,
|
37 |
+
"9": 301,
|
38 |
+
"10": 333,
|
39 |
+
"11": 336,
|
40 |
+
"12": 339,
|
41 |
+
"13": 340,
|
42 |
+
"14": 341,
|
43 |
+
"15": 381,
|
44 |
+
"16": 434,
|
45 |
+
"17": 442,
|
46 |
+
"18": 456,
|
47 |
+
"19": 496,
|
48 |
+
"20": 497,
|
49 |
+
"21": 498,
|
50 |
+
"22": 500,
|
51 |
+
"23": 509,
|
52 |
+
"24": 534,
|
53 |
+
"25": 555,
|
54 |
+
"26": 574,
|
55 |
+
"27": 616,
|
56 |
+
"28": 623,
|
57 |
+
"29": 624,
|
58 |
+
"30": 629,
|
59 |
+
"31": 654,
|
60 |
+
"32": 683,
|
61 |
+
"33": 752,
|
62 |
+
"34": 759,
|
63 |
+
"35": 764,
|
64 |
+
"36": 771,
|
65 |
+
"37": 773,
|
66 |
+
"38": 778,
|
67 |
+
"39": 783,
|
68 |
+
"40": 805,
|
69 |
+
"41": 851,
|
70 |
+
"42": 853,
|
71 |
+
"43": 885,
|
72 |
+
"44": 891,
|
73 |
+
"45": 893,
|
74 |
+
"46": 897,
|
75 |
+
"47": 960,
|
76 |
+
"48": 962,
|
77 |
+
"49": 975,
|
78 |
+
"50": 1023,
|
79 |
+
"51": 1040,
|
80 |
+
"52": 1054,
|
81 |
+
"53": 1068,
|
82 |
+
"54": 1070,
|
83 |
+
"55": 1076,
|
84 |
+
"56": 1101,
|
85 |
+
"57": 1110,
|
86 |
+
"58": 1111,
|
87 |
+
"59": 1112,
|
88 |
+
"60": 1115,
|
89 |
+
"61": 1117,
|
90 |
+
"62": 1119,
|
91 |
+
"63": 1120,
|
92 |
+
"64": 1134,
|
93 |
+
"65": 1136,
|
94 |
+
"66": 1144,
|
95 |
+
"67": 1146,
|
96 |
+
"68": 1148,
|
97 |
+
"69": 1149,
|
98 |
+
"70": 1154,
|
99 |
+
"71": 1178,
|
100 |
+
"72": 1186,
|
101 |
+
"73": 1206,
|
102 |
+
"74": 1213,
|
103 |
+
"75": 1223,
|
104 |
+
"76": 1232,
|
105 |
+
"77": 1243,
|
106 |
+
"78": 1244,
|
107 |
+
"79": 1249,
|
108 |
+
"80": 1274,
|
109 |
+
"81": 1298,
|
110 |
+
"82": 1359,
|
111 |
+
"83": 1368,
|
112 |
+
"84": 1387,
|
113 |
+
"85": 1388,
|
114 |
+
"86": 1389,
|
115 |
+
"87": 1390,
|
116 |
+
"88": 1391,
|
117 |
+
"89": 1392,
|
118 |
+
"90": 1393,
|
119 |
+
"91": 1394,
|
120 |
+
"92": 1395,
|
121 |
+
"93": 1408,
|
122 |
+
"94": 1411,
|
123 |
+
"95": 1425,
|
124 |
+
"96": 1481,
|
125 |
+
"97": 1482,
|
126 |
+
"98": 1483,
|
127 |
+
"99": 1485,
|
128 |
+
"100": 1488,
|
129 |
+
"101": 1491,
|
130 |
+
"102": 1492,
|
131 |
+
"103": 1509,
|
132 |
+
"104": 1510,
|
133 |
+
"105": 1511,
|
134 |
+
"106": 1513,
|
135 |
+
"107": 1514,
|
136 |
+
"108": 1518
|
137 |
+
},
|
138 |
+
"ignore_attention_mask": false,
|
139 |
+
"initializer_range": 0.02,
|
140 |
+
"intermediate_size": 3072,
|
141 |
+
"label2id": {
|
142 |
+
"28": 0,
|
143 |
+
"97": 1,
|
144 |
+
"117": 2,
|
145 |
+
"177": 3,
|
146 |
+
"186": 4,
|
147 |
+
"187": 5,
|
148 |
+
"219": 6,
|
149 |
+
"282": 7,
|
150 |
+
"289": 8,
|
151 |
+
"301": 9,
|
152 |
+
"333": 10,
|
153 |
+
"336": 11,
|
154 |
+
"339": 12,
|
155 |
+
"340": 13,
|
156 |
+
"341": 14,
|
157 |
+
"381": 15,
|
158 |
+
"434": 16,
|
159 |
+
"442": 17,
|
160 |
+
"456": 18,
|
161 |
+
"496": 19,
|
162 |
+
"497": 20,
|
163 |
+
"498": 21,
|
164 |
+
"500": 22,
|
165 |
+
"509": 23,
|
166 |
+
"534": 24,
|
167 |
+
"555": 25,
|
168 |
+
"574": 26,
|
169 |
+
"616": 27,
|
170 |
+
"623": 28,
|
171 |
+
"624": 29,
|
172 |
+
"629": 30,
|
173 |
+
"654": 31,
|
174 |
+
"683": 32,
|
175 |
+
"752": 33,
|
176 |
+
"759": 34,
|
177 |
+
"764": 35,
|
178 |
+
"771": 36,
|
179 |
+
"773": 37,
|
180 |
+
"778": 38,
|
181 |
+
"783": 39,
|
182 |
+
"805": 40,
|
183 |
+
"851": 41,
|
184 |
+
"853": 42,
|
185 |
+
"885": 43,
|
186 |
+
"891": 44,
|
187 |
+
"893": 45,
|
188 |
+
"897": 46,
|
189 |
+
"960": 47,
|
190 |
+
"962": 48,
|
191 |
+
"975": 49,
|
192 |
+
"1023": 50,
|
193 |
+
"1040": 51,
|
194 |
+
"1054": 52,
|
195 |
+
"1068": 53,
|
196 |
+
"1070": 54,
|
197 |
+
"1076": 55,
|
198 |
+
"1101": 56,
|
199 |
+
"1110": 57,
|
200 |
+
"1111": 58,
|
201 |
+
"1112": 59,
|
202 |
+
"1115": 60,
|
203 |
+
"1117": 61,
|
204 |
+
"1119": 62,
|
205 |
+
"1120": 63,
|
206 |
+
"1134": 64,
|
207 |
+
"1136": 65,
|
208 |
+
"1144": 66,
|
209 |
+
"1146": 67,
|
210 |
+
"1148": 68,
|
211 |
+
"1149": 69,
|
212 |
+
"1154": 70,
|
213 |
+
"1178": 71,
|
214 |
+
"1186": 72,
|
215 |
+
"1206": 73,
|
216 |
+
"1213": 74,
|
217 |
+
"1223": 75,
|
218 |
+
"1232": 76,
|
219 |
+
"1243": 77,
|
220 |
+
"1244": 78,
|
221 |
+
"1249": 79,
|
222 |
+
"1274": 80,
|
223 |
+
"1298": 81,
|
224 |
+
"1359": 82,
|
225 |
+
"1368": 83,
|
226 |
+
"1387": 84,
|
227 |
+
"1388": 85,
|
228 |
+
"1389": 86,
|
229 |
+
"1390": 87,
|
230 |
+
"1391": 88,
|
231 |
+
"1392": 89,
|
232 |
+
"1393": 90,
|
233 |
+
"1394": 91,
|
234 |
+
"1395": 92,
|
235 |
+
"1408": 93,
|
236 |
+
"1411": 94,
|
237 |
+
"1425": 95,
|
238 |
+
"1481": 96,
|
239 |
+
"1482": 97,
|
240 |
+
"1483": 98,
|
241 |
+
"1485": 99,
|
242 |
+
"1488": 100,
|
243 |
+
"1491": 101,
|
244 |
+
"1492": 102,
|
245 |
+
"1509": 103,
|
246 |
+
"1510": 104,
|
247 |
+
"1511": 105,
|
248 |
+
"1513": 106,
|
249 |
+
"1514": 107,
|
250 |
+
"1518": 108
|
251 |
+
},
|
252 |
+
"layer_norm_eps": 1e-05,
|
253 |
+
"max_position_embeddings": 4098,
|
254 |
+
"model_type": "longformer",
|
255 |
+
"num_attention_heads": 12,
|
256 |
+
"num_hidden_layers": 12,
|
257 |
+
"onnx_export": false,
|
258 |
+
"pad_token_id": 1,
|
259 |
+
"problem_type": "single_label_classification",
|
260 |
+
"sep_token_id": 2,
|
261 |
+
"torch_dtype": "float32",
|
262 |
+
"transformers_version": "4.51.3",
|
263 |
+
"type_vocab_size": 1,
|
264 |
+
"vocab_size": 50265
|
265 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:297f6786b273c6b2bfb8fb1825c4d6e4f95021ebb9893524b73c92ac7a630978
|
3 |
+
size 595007316
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"extra_special_tokens": {},
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"model_max_length": 1000000000000000019884624838656,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "LongformerTokenizer",
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b930e5d26dea1e73273fa2ec02bef9a8b67be91503334b2d83b6f6aab4391736
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|