NourMohamed91
commited on
Commit
·
4114bf4
1
Parent(s):
cacc7f9
Training in progress epoch 0
Browse files- README.md +6 -15
- config.json +8 -1
- tf_model.h5 +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +113 -105
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# NourMohamed91/v_model
|
14 |
|
15 |
-
This model is a fine-tuned version of [
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
- Validation Loss: 0.
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,16 +42,7 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
|
|
46 |
-
| 2.0015 | 0.8037 | 1 |
|
47 |
-
| 0.5024 | 0.2182 | 2 |
|
48 |
-
| 0.2099 | 0.1322 | 3 |
|
49 |
-
| 0.1471 | 0.1038 | 4 |
|
50 |
-
| 0.1322 | 0.1149 | 5 |
|
51 |
-
| 0.1078 | 0.1052 | 6 |
|
52 |
-
| 0.1011 | 0.0798 | 7 |
|
53 |
-
| 0.0877 | 0.0750 | 8 |
|
54 |
-
| 0.0844 | 0.0797 | 9 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: gp-tar4/QA_FineTuned_Arabert
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
|
|
12 |
|
13 |
# NourMohamed91/v_model
|
14 |
|
15 |
+
This model is a fine-tuned version of [gp-tar4/QA_FineTuned_Arabert](https://huggingface.co/gp-tar4/QA_FineTuned_Arabert) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 2.0085
|
18 |
+
- Validation Loss: 0.3095
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 2.0085 | 0.3095 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
config.json
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 768,
|
@@ -16,7 +17,13 @@
|
|
16 |
"num_attention_heads": 12,
|
17 |
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
19 |
"position_embedding_type": "absolute",
|
|
|
20 |
"transformers_version": "4.42.4",
|
21 |
"type_vocab_size": 2,
|
22 |
"use_cache": true,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gp-tar4/QA_FineTuned_Arabert",
|
3 |
"architectures": [
|
4 |
"BertForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
|
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 0,
|
20 |
+
"pooler_fc_size": 768,
|
21 |
+
"pooler_num_attention_heads": 12,
|
22 |
+
"pooler_num_fc_layers": 3,
|
23 |
+
"pooler_size_per_head": 128,
|
24 |
+
"pooler_type": "first_token_transform",
|
25 |
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.42.4",
|
28 |
"type_vocab_size": 2,
|
29 |
"use_cache": true,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 538686416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f13b29ff7f7176a04e6d62944424bee8ed886a1b84016fe9f5f6d9feb20adc4d
|
3 |
size 538686416
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "+ا",
|
5 |
"lstrip": false,
|
6 |
"normalized": true,
|
@@ -8,284 +8,284 @@
|
|
8 |
"single_word": true,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": true,
|
15 |
"rstrip": false,
|
16 |
"single_word": true,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": true,
|
23 |
"rstrip": false,
|
24 |
"single_word": true,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": true,
|
31 |
"rstrip": false,
|
32 |
"single_word": true,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
-
"content": "
|
37 |
"lstrip": false,
|
38 |
"normalized": true,
|
39 |
"rstrip": false,
|
40 |
"single_word": true,
|
41 |
"special": true
|
42 |
},
|
43 |
-
"
|
44 |
-
"content": "
|
45 |
"lstrip": false,
|
46 |
"normalized": true,
|
47 |
"rstrip": false,
|
48 |
"single_word": true,
|
49 |
"special": true
|
50 |
},
|
51 |
-
"
|
52 |
-
"content": "
|
53 |
"lstrip": false,
|
54 |
"normalized": true,
|
55 |
"rstrip": false,
|
56 |
"single_word": true,
|
57 |
"special": true
|
58 |
},
|
59 |
-
"
|
60 |
-
"content": "
|
61 |
"lstrip": false,
|
62 |
"normalized": true,
|
63 |
"rstrip": false,
|
64 |
"single_word": true,
|
65 |
"special": true
|
66 |
},
|
67 |
-
"
|
68 |
-
"content": "
|
69 |
"lstrip": false,
|
70 |
"normalized": true,
|
71 |
"rstrip": false,
|
72 |
"single_word": true,
|
73 |
"special": true
|
74 |
},
|
75 |
-
"
|
76 |
-
"content": "
|
77 |
"lstrip": false,
|
78 |
"normalized": true,
|
79 |
"rstrip": false,
|
80 |
"single_word": true,
|
81 |
"special": true
|
82 |
},
|
83 |
-
"
|
84 |
-
"content": "
|
85 |
"lstrip": false,
|
86 |
"normalized": true,
|
87 |
"rstrip": false,
|
88 |
"single_word": true,
|
89 |
"special": true
|
90 |
},
|
91 |
-
"
|
92 |
-
"content": "
|
93 |
"lstrip": false,
|
94 |
"normalized": true,
|
95 |
"rstrip": false,
|
96 |
"single_word": true,
|
97 |
"special": true
|
98 |
},
|
99 |
-
"
|
100 |
-
"content": "
|
101 |
"lstrip": false,
|
102 |
"normalized": true,
|
103 |
"rstrip": false,
|
104 |
"single_word": true,
|
105 |
"special": true
|
106 |
},
|
107 |
-
"
|
108 |
-
"content": "
|
109 |
"lstrip": false,
|
110 |
"normalized": true,
|
111 |
"rstrip": false,
|
112 |
"single_word": true,
|
113 |
"special": true
|
114 |
},
|
115 |
-
"
|
116 |
-
"content": "
|
117 |
"lstrip": false,
|
118 |
"normalized": true,
|
119 |
"rstrip": false,
|
120 |
"single_word": true,
|
121 |
"special": true
|
122 |
},
|
123 |
-
"
|
124 |
-
"content": "
|
125 |
"lstrip": false,
|
126 |
"normalized": true,
|
127 |
"rstrip": false,
|
128 |
"single_word": true,
|
129 |
"special": true
|
130 |
},
|
131 |
-
"
|
132 |
-
"content": "
|
133 |
"lstrip": false,
|
134 |
"normalized": true,
|
135 |
"rstrip": false,
|
136 |
"single_word": true,
|
137 |
"special": true
|
138 |
},
|
139 |
-
"
|
140 |
-
"content": "
|
141 |
"lstrip": false,
|
142 |
"normalized": true,
|
143 |
"rstrip": false,
|
144 |
"single_word": true,
|
145 |
"special": true
|
146 |
},
|
147 |
-
"
|
148 |
-
"content": "
|
149 |
"lstrip": false,
|
150 |
"normalized": true,
|
151 |
"rstrip": false,
|
152 |
"single_word": true,
|
153 |
"special": true
|
154 |
},
|
155 |
-
"
|
156 |
-
"content": "
|
157 |
"lstrip": false,
|
158 |
"normalized": true,
|
159 |
"rstrip": false,
|
160 |
"single_word": true,
|
161 |
"special": true
|
162 |
},
|
163 |
-
"
|
164 |
-
"content": "
|
165 |
"lstrip": false,
|
166 |
"normalized": true,
|
167 |
"rstrip": false,
|
168 |
"single_word": true,
|
169 |
"special": true
|
170 |
},
|
171 |
-
"
|
172 |
-
"content": "
|
173 |
"lstrip": false,
|
174 |
"normalized": true,
|
175 |
"rstrip": false,
|
176 |
"single_word": true,
|
177 |
"special": true
|
178 |
},
|
179 |
-
"
|
180 |
-
"content": "
|
181 |
"lstrip": false,
|
182 |
"normalized": true,
|
183 |
"rstrip": false,
|
184 |
"single_word": true,
|
185 |
"special": true
|
186 |
},
|
187 |
-
"
|
188 |
-
"content": "
|
189 |
"lstrip": false,
|
190 |
"normalized": true,
|
191 |
"rstrip": false,
|
192 |
"single_word": true,
|
193 |
"special": true
|
194 |
},
|
195 |
-
"
|
196 |
-
"content": "
|
197 |
"lstrip": false,
|
198 |
"normalized": true,
|
199 |
"rstrip": false,
|
200 |
"single_word": true,
|
201 |
"special": true
|
202 |
},
|
203 |
-
"
|
204 |
-
"content": "
|
205 |
"lstrip": false,
|
206 |
"normalized": true,
|
207 |
"rstrip": false,
|
208 |
"single_word": true,
|
209 |
"special": true
|
210 |
},
|
211 |
-
"
|
212 |
-
"content": "
|
213 |
"lstrip": false,
|
214 |
"normalized": true,
|
215 |
"rstrip": false,
|
216 |
"single_word": true,
|
217 |
"special": true
|
218 |
},
|
219 |
-
"
|
220 |
-
"content": "
|
221 |
"lstrip": false,
|
222 |
"normalized": true,
|
223 |
"rstrip": false,
|
224 |
"single_word": true,
|
225 |
"special": true
|
226 |
},
|
227 |
-
"
|
228 |
-
"content": "
|
229 |
"lstrip": false,
|
230 |
-
"normalized":
|
231 |
"rstrip": false,
|
232 |
-
"single_word":
|
233 |
"special": true
|
234 |
},
|
235 |
-
"
|
236 |
-
"content": "
|
237 |
"lstrip": false,
|
238 |
-
"normalized":
|
239 |
"rstrip": false,
|
240 |
-
"single_word":
|
241 |
"special": true
|
242 |
},
|
243 |
-
"
|
244 |
-
"content": "
|
245 |
"lstrip": false,
|
246 |
-
"normalized":
|
247 |
"rstrip": false,
|
248 |
-
"single_word":
|
249 |
"special": true
|
250 |
},
|
251 |
-
"
|
252 |
-
"content": "[
|
253 |
"lstrip": false,
|
254 |
"normalized": false,
|
255 |
"rstrip": false,
|
256 |
"single_word": false,
|
257 |
"special": true
|
258 |
},
|
259 |
-
"
|
260 |
-
"content": "[
|
261 |
"lstrip": false,
|
262 |
"normalized": false,
|
263 |
"rstrip": false,
|
264 |
"single_word": false,
|
265 |
"special": true
|
266 |
},
|
267 |
-
"
|
268 |
-
"content": "[
|
269 |
"lstrip": false,
|
270 |
-
"normalized":
|
271 |
"rstrip": false,
|
272 |
-
"single_word":
|
273 |
"special": true
|
274 |
},
|
275 |
-
"
|
276 |
-
"content": "[
|
277 |
"lstrip": false,
|
278 |
-
"normalized":
|
279 |
"rstrip": false,
|
280 |
-
"single_word":
|
281 |
"special": true
|
282 |
},
|
283 |
-
"
|
284 |
-
"content": "[
|
285 |
"lstrip": false,
|
286 |
-
"normalized":
|
287 |
"rstrip": false,
|
288 |
-
"single_word":
|
289 |
"special": true
|
290 |
}
|
291 |
},
|
@@ -293,46 +293,54 @@
|
|
293 |
"cls_token": "[CLS]",
|
294 |
"do_basic_tokenize": true,
|
295 |
"do_lower_case": false,
|
|
|
296 |
"mask_token": "[MASK]",
|
297 |
"max_len": 512,
|
|
|
298 |
"model_max_length": 512,
|
299 |
"never_split": [
|
300 |
-
"+ك",
|
301 |
-
"+كما",
|
302 |
-
"ك+",
|
303 |
"+وا",
|
304 |
-
"
|
305 |
-
"
|
306 |
-
"
|
307 |
-
"+ان",
|
308 |
"+هم",
|
309 |
"+ة",
|
310 |
-
"[بريد]",
|
311 |
-
"لل+",
|
312 |
-
"+ي",
|
313 |
-
"+ت",
|
314 |
"+ن",
|
315 |
-
"
|
316 |
-
"
|
317 |
-
"[
|
318 |
-
"
|
|
|
319 |
"+ا",
|
|
|
|
|
320 |
"ب+",
|
321 |
-
"ف+",
|
322 |
"+نا",
|
323 |
-
"
|
324 |
-
"
|
|
|
|
|
325 |
"+هما",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
326 |
"ال+",
|
327 |
-
"
|
328 |
-
"+هن",
|
329 |
-
"+ات",
|
330 |
-
"[رابط]"
|
331 |
],
|
|
|
332 |
"pad_token": "[PAD]",
|
|
|
|
|
333 |
"sep_token": "[SEP]",
|
|
|
334 |
"strip_accents": null,
|
335 |
"tokenize_chinese_chars": true,
|
336 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
337 |
"unk_token": "[UNK]"
|
338 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"124": {
|
4 |
"content": "+ا",
|
5 |
"lstrip": false,
|
6 |
"normalized": true,
|
|
|
8 |
"single_word": true,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"125": {
|
12 |
+
"content": "+ة",
|
13 |
"lstrip": false,
|
14 |
"normalized": true,
|
15 |
"rstrip": false,
|
16 |
"single_word": true,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"126": {
|
20 |
+
"content": "+ت",
|
21 |
"lstrip": false,
|
22 |
"normalized": true,
|
23 |
"rstrip": false,
|
24 |
"single_word": true,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"127": {
|
28 |
+
"content": "+ك",
|
29 |
"lstrip": false,
|
30 |
"normalized": true,
|
31 |
"rstrip": false,
|
32 |
"single_word": true,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"128": {
|
36 |
+
"content": "+ن",
|
37 |
"lstrip": false,
|
38 |
"normalized": true,
|
39 |
"rstrip": false,
|
40 |
"single_word": true,
|
41 |
"special": true
|
42 |
},
|
43 |
+
"129": {
|
44 |
+
"content": "+ه",
|
45 |
"lstrip": false,
|
46 |
"normalized": true,
|
47 |
"rstrip": false,
|
48 |
"single_word": true,
|
49 |
"special": true
|
50 |
},
|
51 |
+
"130": {
|
52 |
+
"content": "+ي",
|
53 |
"lstrip": false,
|
54 |
"normalized": true,
|
55 |
"rstrip": false,
|
56 |
"single_word": true,
|
57 |
"special": true
|
58 |
},
|
59 |
+
"448": {
|
60 |
+
"content": "ب+",
|
61 |
"lstrip": false,
|
62 |
"normalized": true,
|
63 |
"rstrip": false,
|
64 |
"single_word": true,
|
65 |
"special": true
|
66 |
},
|
67 |
+
"635": {
|
68 |
+
"content": "س+",
|
69 |
"lstrip": false,
|
70 |
"normalized": true,
|
71 |
"rstrip": false,
|
72 |
"single_word": true,
|
73 |
"special": true
|
74 |
},
|
75 |
+
"765": {
|
76 |
+
"content": "ف+",
|
77 |
"lstrip": false,
|
78 |
"normalized": true,
|
79 |
"rstrip": false,
|
80 |
"single_word": true,
|
81 |
"special": true
|
82 |
},
|
83 |
+
"802": {
|
84 |
+
"content": "ك+",
|
85 |
"lstrip": false,
|
86 |
"normalized": true,
|
87 |
"rstrip": false,
|
88 |
"single_word": true,
|
89 |
"special": true
|
90 |
},
|
91 |
+
"816": {
|
92 |
+
"content": "ل+",
|
93 |
"lstrip": false,
|
94 |
"normalized": true,
|
95 |
"rstrip": false,
|
96 |
"single_word": true,
|
97 |
"special": true
|
98 |
},
|
99 |
+
"897": {
|
100 |
+
"content": "و+",
|
101 |
"lstrip": false,
|
102 |
"normalized": true,
|
103 |
"rstrip": false,
|
104 |
"single_word": true,
|
105 |
"special": true
|
106 |
},
|
107 |
+
"1012": {
|
108 |
+
"content": "+ات",
|
109 |
"lstrip": false,
|
110 |
"normalized": true,
|
111 |
"rstrip": false,
|
112 |
"single_word": true,
|
113 |
"special": true
|
114 |
},
|
115 |
+
"1013": {
|
116 |
+
"content": "+ان",
|
117 |
"lstrip": false,
|
118 |
"normalized": true,
|
119 |
"rstrip": false,
|
120 |
"single_word": true,
|
121 |
"special": true
|
122 |
},
|
123 |
+
"1015": {
|
124 |
+
"content": "+كم",
|
125 |
"lstrip": false,
|
126 |
"normalized": true,
|
127 |
"rstrip": false,
|
128 |
"single_word": true,
|
129 |
"special": true
|
130 |
},
|
131 |
+
"1016": {
|
132 |
+
"content": "+كن",
|
133 |
"lstrip": false,
|
134 |
"normalized": true,
|
135 |
"rstrip": false,
|
136 |
"single_word": true,
|
137 |
"special": true
|
138 |
},
|
139 |
+
"1017": {
|
140 |
+
"content": "+نا",
|
141 |
"lstrip": false,
|
142 |
"normalized": true,
|
143 |
"rstrip": false,
|
144 |
"single_word": true,
|
145 |
"special": true
|
146 |
},
|
147 |
+
"1018": {
|
148 |
+
"content": "+ها",
|
149 |
"lstrip": false,
|
150 |
"normalized": true,
|
151 |
"rstrip": false,
|
152 |
"single_word": true,
|
153 |
"special": true
|
154 |
},
|
155 |
+
"1019": {
|
156 |
+
"content": "+هم",
|
157 |
"lstrip": false,
|
158 |
"normalized": true,
|
159 |
"rstrip": false,
|
160 |
"single_word": true,
|
161 |
"special": true
|
162 |
},
|
163 |
+
"1020": {
|
164 |
+
"content": "+هن",
|
165 |
"lstrip": false,
|
166 |
"normalized": true,
|
167 |
"rstrip": false,
|
168 |
"single_word": true,
|
169 |
"special": true
|
170 |
},
|
171 |
+
"1021": {
|
172 |
+
"content": "+وا",
|
173 |
"lstrip": false,
|
174 |
"normalized": true,
|
175 |
"rstrip": false,
|
176 |
"single_word": true,
|
177 |
"special": true
|
178 |
},
|
179 |
+
"1022": {
|
180 |
+
"content": "+ون",
|
181 |
"lstrip": false,
|
182 |
"normalized": true,
|
183 |
"rstrip": false,
|
184 |
"single_word": true,
|
185 |
"special": true
|
186 |
},
|
187 |
+
"1023": {
|
188 |
+
"content": "+ين",
|
189 |
"lstrip": false,
|
190 |
"normalized": true,
|
191 |
"rstrip": false,
|
192 |
"single_word": true,
|
193 |
"special": true
|
194 |
},
|
195 |
+
"3000": {
|
196 |
+
"content": "ال+",
|
197 |
"lstrip": false,
|
198 |
"normalized": true,
|
199 |
"rstrip": false,
|
200 |
"single_word": true,
|
201 |
"special": true
|
202 |
},
|
203 |
+
"6154": {
|
204 |
+
"content": "لل+",
|
205 |
"lstrip": false,
|
206 |
"normalized": true,
|
207 |
"rstrip": false,
|
208 |
"single_word": true,
|
209 |
"special": true
|
210 |
},
|
211 |
+
"8270": {
|
212 |
+
"content": "+كما",
|
213 |
"lstrip": false,
|
214 |
"normalized": true,
|
215 |
"rstrip": false,
|
216 |
"single_word": true,
|
217 |
"special": true
|
218 |
},
|
219 |
+
"8271": {
|
220 |
+
"content": "+هما",
|
221 |
"lstrip": false,
|
222 |
"normalized": true,
|
223 |
"rstrip": false,
|
224 |
"single_word": true,
|
225 |
"special": true
|
226 |
},
|
227 |
+
"29756": {
|
228 |
+
"content": "[CLS]",
|
229 |
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
"special": true
|
234 |
},
|
235 |
+
"29757": {
|
236 |
+
"content": "[PAD]",
|
237 |
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
"special": true
|
242 |
},
|
243 |
+
"29758": {
|
244 |
+
"content": "[SEP]",
|
245 |
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
"special": true
|
250 |
},
|
251 |
+
"29759": {
|
252 |
+
"content": "[UNK]",
|
253 |
"lstrip": false,
|
254 |
"normalized": false,
|
255 |
"rstrip": false,
|
256 |
"single_word": false,
|
257 |
"special": true
|
258 |
},
|
259 |
+
"46585": {
|
260 |
+
"content": "[MASK]",
|
261 |
"lstrip": false,
|
262 |
"normalized": false,
|
263 |
"rstrip": false,
|
264 |
"single_word": false,
|
265 |
"special": true
|
266 |
},
|
267 |
+
"46586": {
|
268 |
+
"content": "[بريد]",
|
269 |
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
"rstrip": false,
|
272 |
+
"single_word": true,
|
273 |
"special": true
|
274 |
},
|
275 |
+
"46587": {
|
276 |
+
"content": "[رابط]",
|
277 |
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
"rstrip": false,
|
280 |
+
"single_word": true,
|
281 |
"special": true
|
282 |
},
|
283 |
+
"57701": {
|
284 |
+
"content": "[مستخدم]",
|
285 |
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
"rstrip": false,
|
288 |
+
"single_word": true,
|
289 |
"special": true
|
290 |
}
|
291 |
},
|
|
|
293 |
"cls_token": "[CLS]",
|
294 |
"do_basic_tokenize": true,
|
295 |
"do_lower_case": false,
|
296 |
+
"full_tokenizer_file": null,
|
297 |
"mask_token": "[MASK]",
|
298 |
"max_len": 512,
|
299 |
+
"max_length": 384,
|
300 |
"model_max_length": 512,
|
301 |
"never_split": [
|
|
|
|
|
|
|
302 |
"+وا",
|
303 |
+
"س+",
|
304 |
+
"[مستخدم]",
|
305 |
+
"+ك",
|
|
|
306 |
"+هم",
|
307 |
"+ة",
|
|
|
|
|
|
|
|
|
308 |
"+ن",
|
309 |
+
"لل+",
|
310 |
+
"[بريد]",
|
311 |
+
"[رابط]",
|
312 |
+
"+ه",
|
313 |
+
"+كن",
|
314 |
"+ا",
|
315 |
+
"+ات",
|
316 |
+
"+ي",
|
317 |
"ب+",
|
|
|
318 |
"+نا",
|
319 |
+
"+هن",
|
320 |
+
"+كم",
|
321 |
+
"ك+",
|
322 |
+
"+ين",
|
323 |
"+هما",
|
324 |
+
"و+",
|
325 |
+
"+كما",
|
326 |
+
"+ان",
|
327 |
+
"+ت",
|
328 |
+
"+ون",
|
329 |
+
"ل+",
|
330 |
+
"+ها",
|
331 |
"ال+",
|
332 |
+
"ف+"
|
|
|
|
|
|
|
333 |
],
|
334 |
+
"pad_to_multiple_of": null,
|
335 |
"pad_token": "[PAD]",
|
336 |
+
"pad_token_type_id": 0,
|
337 |
+
"padding_side": "right",
|
338 |
"sep_token": "[SEP]",
|
339 |
+
"stride": 0,
|
340 |
"strip_accents": null,
|
341 |
"tokenize_chinese_chars": true,
|
342 |
"tokenizer_class": "BertTokenizer",
|
343 |
+
"truncation_side": "right",
|
344 |
+
"truncation_strategy": "only_second",
|
345 |
"unk_token": "[UNK]"
|
346 |
}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|