init
Browse files- config.json +57 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +769 -0
- tokenizer_config.json +436 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/m2",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 128,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "art",
|
14 |
+
"2": "building",
|
15 |
+
"3": "event",
|
16 |
+
"4": "location",
|
17 |
+
"5": "org",
|
18 |
+
"6": "other",
|
19 |
+
"7": "person",
|
20 |
+
"8": "product",
|
21 |
+
"9": "etc-0",
|
22 |
+
"10": "etc-1",
|
23 |
+
"11": "etc-2",
|
24 |
+
"12": "etc-3"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 448,
|
28 |
+
"label2id": {
|
29 |
+
"O": 0,
|
30 |
+
"art": 1,
|
31 |
+
"building": 2,
|
32 |
+
"etc-0": 9,
|
33 |
+
"etc-1": 10,
|
34 |
+
"etc-2": 11,
|
35 |
+
"etc-3": 12,
|
36 |
+
"event": 3,
|
37 |
+
"location": 4,
|
38 |
+
"org": 5,
|
39 |
+
"other": 6,
|
40 |
+
"person": 7,
|
41 |
+
"product": 8
|
42 |
+
},
|
43 |
+
"max_position_embeddings": 1024,
|
44 |
+
"model_type": "mistral",
|
45 |
+
"num_attention_heads": 32,
|
46 |
+
"num_hidden_layers": 2,
|
47 |
+
"num_key_value_heads": 8,
|
48 |
+
"pad_token_id": 3,
|
49 |
+
"rms_norm_eps": 1e-05,
|
50 |
+
"rope_theta": 1000000.0,
|
51 |
+
"sliding_window": null,
|
52 |
+
"tie_word_embeddings": false,
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.41.2",
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 256
|
57 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 770,
|
6 |
+
"transformers_version": "4.41.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52af08dd69cd667de911cc318c26b954676fa79f361bd5638fd23e688f616f3e
|
3 |
+
size 1970840
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.json
ADDED
@@ -0,0 +1,769 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<unk>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "<s>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "</s>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "UNKNOWN_0",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "UNKNOWN_1",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 5,
|
53 |
+
"content": "UNKNOWN_2",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 6,
|
62 |
+
"content": "UNKNOWN_3",
|
63 |
+
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"normalized": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"id": 7,
|
71 |
+
"content": "UNKNOWN_4",
|
72 |
+
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"normalized": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"id": 8,
|
80 |
+
"content": "UNKNOWN_5",
|
81 |
+
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"special": true
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"id": 9,
|
89 |
+
"content": "UNKNOWN_6",
|
90 |
+
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"normalized": false,
|
94 |
+
"special": true
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"id": 10,
|
98 |
+
"content": "UNKNOWN_7",
|
99 |
+
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"special": true
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"id": 11,
|
107 |
+
"content": "UNKNOWN_8",
|
108 |
+
"single_word": false,
|
109 |
+
"lstrip": false,
|
110 |
+
"rstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"special": true
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"id": 12,
|
116 |
+
"content": "UNKNOWN_9",
|
117 |
+
"single_word": false,
|
118 |
+
"lstrip": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"id": 13,
|
125 |
+
"content": "UNKNOWN_10",
|
126 |
+
"single_word": false,
|
127 |
+
"lstrip": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"id": 14,
|
134 |
+
"content": "UNKNOWN_11",
|
135 |
+
"single_word": false,
|
136 |
+
"lstrip": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"normalized": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"id": 15,
|
143 |
+
"content": "UNKNOWN_12",
|
144 |
+
"single_word": false,
|
145 |
+
"lstrip": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"normalized": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"id": 16,
|
152 |
+
"content": "UNKNOWN_13",
|
153 |
+
"single_word": false,
|
154 |
+
"lstrip": false,
|
155 |
+
"rstrip": false,
|
156 |
+
"normalized": false,
|
157 |
+
"special": true
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"id": 17,
|
161 |
+
"content": "UNKNOWN_14",
|
162 |
+
"single_word": false,
|
163 |
+
"lstrip": false,
|
164 |
+
"rstrip": false,
|
165 |
+
"normalized": false,
|
166 |
+
"special": true
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"id": 18,
|
170 |
+
"content": "UNKNOWN_15",
|
171 |
+
"single_word": false,
|
172 |
+
"lstrip": false,
|
173 |
+
"rstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"special": true
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"id": 19,
|
179 |
+
"content": "UNKNOWN_16",
|
180 |
+
"single_word": false,
|
181 |
+
"lstrip": false,
|
182 |
+
"rstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"special": true
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"id": 20,
|
188 |
+
"content": "UNKNOWN_17",
|
189 |
+
"single_word": false,
|
190 |
+
"lstrip": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"id": 21,
|
197 |
+
"content": "UNKNOWN_18",
|
198 |
+
"single_word": false,
|
199 |
+
"lstrip": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"id": 22,
|
206 |
+
"content": "UNKNOWN_19",
|
207 |
+
"single_word": false,
|
208 |
+
"lstrip": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"normalized": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"id": 23,
|
215 |
+
"content": "UNKNOWN_20",
|
216 |
+
"single_word": false,
|
217 |
+
"lstrip": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"normalized": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"id": 24,
|
224 |
+
"content": "UNKNOWN_21",
|
225 |
+
"single_word": false,
|
226 |
+
"lstrip": false,
|
227 |
+
"rstrip": false,
|
228 |
+
"normalized": false,
|
229 |
+
"special": true
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"id": 25,
|
233 |
+
"content": "UNKNOWN_22",
|
234 |
+
"single_word": false,
|
235 |
+
"lstrip": false,
|
236 |
+
"rstrip": false,
|
237 |
+
"normalized": false,
|
238 |
+
"special": true
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"id": 26,
|
242 |
+
"content": "UNKNOWN_23",
|
243 |
+
"single_word": false,
|
244 |
+
"lstrip": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"special": true
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"id": 27,
|
251 |
+
"content": "UNKNOWN_24",
|
252 |
+
"single_word": false,
|
253 |
+
"lstrip": false,
|
254 |
+
"rstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"special": true
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"id": 28,
|
260 |
+
"content": "UNKNOWN_25",
|
261 |
+
"single_word": false,
|
262 |
+
"lstrip": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"id": 29,
|
269 |
+
"content": "UNKNOWN_26",
|
270 |
+
"single_word": false,
|
271 |
+
"lstrip": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"id": 30,
|
278 |
+
"content": "UNKNOWN_27",
|
279 |
+
"single_word": false,
|
280 |
+
"lstrip": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"normalized": false,
|
283 |
+
"special": true
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"id": 31,
|
287 |
+
"content": "UNKNOWN_28",
|
288 |
+
"single_word": false,
|
289 |
+
"lstrip": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"normalized": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"id": 32,
|
296 |
+
"content": "UNKNOWN_29",
|
297 |
+
"single_word": false,
|
298 |
+
"lstrip": false,
|
299 |
+
"rstrip": false,
|
300 |
+
"normalized": false,
|
301 |
+
"special": true
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"id": 33,
|
305 |
+
"content": "UNKNOWN_30",
|
306 |
+
"single_word": false,
|
307 |
+
"lstrip": false,
|
308 |
+
"rstrip": false,
|
309 |
+
"normalized": false,
|
310 |
+
"special": true
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"id": 34,
|
314 |
+
"content": "UNKNOWN_31",
|
315 |
+
"single_word": false,
|
316 |
+
"lstrip": false,
|
317 |
+
"rstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"special": true
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"id": 35,
|
323 |
+
"content": "UNKNOWN_32",
|
324 |
+
"single_word": false,
|
325 |
+
"lstrip": false,
|
326 |
+
"rstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"special": true
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"id": 36,
|
332 |
+
"content": "UNKNOWN_33",
|
333 |
+
"single_word": false,
|
334 |
+
"lstrip": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"id": 37,
|
341 |
+
"content": "UNKNOWN_34",
|
342 |
+
"single_word": false,
|
343 |
+
"lstrip": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"id": 38,
|
350 |
+
"content": "UNKNOWN_35",
|
351 |
+
"single_word": false,
|
352 |
+
"lstrip": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"normalized": false,
|
355 |
+
"special": true
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"id": 39,
|
359 |
+
"content": "UNKNOWN_36",
|
360 |
+
"single_word": false,
|
361 |
+
"lstrip": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"normalized": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"id": 40,
|
368 |
+
"content": "UNKNOWN_37",
|
369 |
+
"single_word": false,
|
370 |
+
"lstrip": false,
|
371 |
+
"rstrip": false,
|
372 |
+
"normalized": false,
|
373 |
+
"special": true
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"id": 41,
|
377 |
+
"content": "UNKNOWN_38",
|
378 |
+
"single_word": false,
|
379 |
+
"lstrip": false,
|
380 |
+
"rstrip": false,
|
381 |
+
"normalized": false,
|
382 |
+
"special": true
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"id": 42,
|
386 |
+
"content": "UNKNOWN_39",
|
387 |
+
"single_word": false,
|
388 |
+
"lstrip": false,
|
389 |
+
"rstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"special": true
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"id": 43,
|
395 |
+
"content": "UNKNOWN_40",
|
396 |
+
"single_word": false,
|
397 |
+
"lstrip": false,
|
398 |
+
"rstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"special": true
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"id": 44,
|
404 |
+
"content": "UNKNOWN_41",
|
405 |
+
"single_word": false,
|
406 |
+
"lstrip": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"normalized": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"id": 45,
|
413 |
+
"content": "UNKNOWN_42",
|
414 |
+
"single_word": false,
|
415 |
+
"lstrip": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"id": 46,
|
422 |
+
"content": "UNKNOWN_43",
|
423 |
+
"single_word": false,
|
424 |
+
"lstrip": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"normalized": false,
|
427 |
+
"special": true
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"id": 47,
|
431 |
+
"content": "UNKNOWN_44",
|
432 |
+
"single_word": false,
|
433 |
+
"lstrip": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"normalized": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"id": 48,
|
440 |
+
"content": "UNKNOWN_45",
|
441 |
+
"single_word": false,
|
442 |
+
"lstrip": false,
|
443 |
+
"rstrip": false,
|
444 |
+
"normalized": false,
|
445 |
+
"special": true
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"id": 49,
|
449 |
+
"content": "UNKNOWN_46",
|
450 |
+
"single_word": false,
|
451 |
+
"lstrip": false,
|
452 |
+
"rstrip": false,
|
453 |
+
"normalized": false,
|
454 |
+
"special": true
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"id": 50,
|
458 |
+
"content": "UNKNOWN_47",
|
459 |
+
"single_word": false,
|
460 |
+
"lstrip": false,
|
461 |
+
"rstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"special": true
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"id": 51,
|
467 |
+
"content": "UNKNOWN_48",
|
468 |
+
"single_word": false,
|
469 |
+
"lstrip": false,
|
470 |
+
"rstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"special": true
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"id": 52,
|
476 |
+
"content": "UNKNOWN_49",
|
477 |
+
"single_word": false,
|
478 |
+
"lstrip": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"normalized": false,
|
481 |
+
"special": true
|
482 |
+
}
|
483 |
+
],
|
484 |
+
"normalizer": {
|
485 |
+
"type": "NFKC"
|
486 |
+
},
|
487 |
+
"pre_tokenizer": {
|
488 |
+
"type": "Metaspace",
|
489 |
+
"replacement": "▁",
|
490 |
+
"prepend_scheme": "always",
|
491 |
+
"split": true
|
492 |
+
},
|
493 |
+
"post_processor": null,
|
494 |
+
"decoder": {
|
495 |
+
"type": "Metaspace",
|
496 |
+
"replacement": "▁",
|
497 |
+
"prepend_scheme": "always",
|
498 |
+
"split": true
|
499 |
+
},
|
500 |
+
"model": {
|
501 |
+
"type": "BPE",
|
502 |
+
"dropout": null,
|
503 |
+
"unk_token": "<unk>",
|
504 |
+
"continuing_subword_prefix": null,
|
505 |
+
"end_of_word_suffix": null,
|
506 |
+
"fuse_unk": false,
|
507 |
+
"byte_fallback": false,
|
508 |
+
"ignore_merges": false,
|
509 |
+
"vocab": {
|
510 |
+
"<unk>": 0,
|
511 |
+
"<s>": 1,
|
512 |
+
"</s>": 2,
|
513 |
+
"UNKNOWN_0": 3,
|
514 |
+
"UNKNOWN_1": 4,
|
515 |
+
"UNKNOWN_2": 5,
|
516 |
+
"UNKNOWN_3": 6,
|
517 |
+
"UNKNOWN_4": 7,
|
518 |
+
"UNKNOWN_5": 8,
|
519 |
+
"UNKNOWN_6": 9,
|
520 |
+
"UNKNOWN_7": 10,
|
521 |
+
"UNKNOWN_8": 11,
|
522 |
+
"UNKNOWN_9": 12,
|
523 |
+
"UNKNOWN_10": 13,
|
524 |
+
"UNKNOWN_11": 14,
|
525 |
+
"UNKNOWN_12": 15,
|
526 |
+
"UNKNOWN_13": 16,
|
527 |
+
"UNKNOWN_14": 17,
|
528 |
+
"UNKNOWN_15": 18,
|
529 |
+
"UNKNOWN_16": 19,
|
530 |
+
"UNKNOWN_17": 20,
|
531 |
+
"UNKNOWN_18": 21,
|
532 |
+
"UNKNOWN_19": 22,
|
533 |
+
"UNKNOWN_20": 23,
|
534 |
+
"UNKNOWN_21": 24,
|
535 |
+
"UNKNOWN_22": 25,
|
536 |
+
"UNKNOWN_23": 26,
|
537 |
+
"UNKNOWN_24": 27,
|
538 |
+
"UNKNOWN_25": 28,
|
539 |
+
"UNKNOWN_26": 29,
|
540 |
+
"UNKNOWN_27": 30,
|
541 |
+
"UNKNOWN_28": 31,
|
542 |
+
"UNKNOWN_29": 32,
|
543 |
+
"UNKNOWN_30": 33,
|
544 |
+
"UNKNOWN_31": 34,
|
545 |
+
"UNKNOWN_32": 35,
|
546 |
+
"UNKNOWN_33": 36,
|
547 |
+
"UNKNOWN_34": 37,
|
548 |
+
"UNKNOWN_35": 38,
|
549 |
+
"UNKNOWN_36": 39,
|
550 |
+
"UNKNOWN_37": 40,
|
551 |
+
"UNKNOWN_38": 41,
|
552 |
+
"UNKNOWN_39": 42,
|
553 |
+
"UNKNOWN_40": 43,
|
554 |
+
"UNKNOWN_41": 44,
|
555 |
+
"UNKNOWN_42": 45,
|
556 |
+
"UNKNOWN_43": 46,
|
557 |
+
"UNKNOWN_44": 47,
|
558 |
+
"UNKNOWN_45": 48,
|
559 |
+
"UNKNOWN_46": 49,
|
560 |
+
"UNKNOWN_47": 50,
|
561 |
+
"UNKNOWN_48": 51,
|
562 |
+
"UNKNOWN_49": 52,
|
563 |
+
"!": 53,
|
564 |
+
"\"": 54,
|
565 |
+
"#": 55,
|
566 |
+
"$": 56,
|
567 |
+
"%": 57,
|
568 |
+
"&": 58,
|
569 |
+
"'": 59,
|
570 |
+
"(": 60,
|
571 |
+
")": 61,
|
572 |
+
"*": 62,
|
573 |
+
"+": 63,
|
574 |
+
"-": 64,
|
575 |
+
".": 65,
|
576 |
+
"/": 66,
|
577 |
+
"0": 67,
|
578 |
+
"1": 68,
|
579 |
+
"2": 69,
|
580 |
+
"3": 70,
|
581 |
+
"4": 71,
|
582 |
+
"5": 72,
|
583 |
+
"6": 73,
|
584 |
+
"7": 74,
|
585 |
+
"8": 75,
|
586 |
+
"9": 76,
|
587 |
+
":": 77,
|
588 |
+
";": 78,
|
589 |
+
"<": 79,
|
590 |
+
"=": 80,
|
591 |
+
">": 81,
|
592 |
+
"?": 82,
|
593 |
+
"@": 83,
|
594 |
+
"A": 84,
|
595 |
+
"B": 85,
|
596 |
+
"C": 86,
|
597 |
+
"D": 87,
|
598 |
+
"E": 88,
|
599 |
+
"F": 89,
|
600 |
+
"G": 90,
|
601 |
+
"H": 91,
|
602 |
+
"I": 92,
|
603 |
+
"J": 93,
|
604 |
+
"K": 94,
|
605 |
+
"L": 95,
|
606 |
+
"M": 96,
|
607 |
+
"N": 97,
|
608 |
+
"O": 98,
|
609 |
+
"P": 99,
|
610 |
+
"Q": 100,
|
611 |
+
"R": 101,
|
612 |
+
"S": 102,
|
613 |
+
"T": 103,
|
614 |
+
"U": 104,
|
615 |
+
"V": 105,
|
616 |
+
"W": 106,
|
617 |
+
"X": 107,
|
618 |
+
"Y": 108,
|
619 |
+
"Z": 109,
|
620 |
+
"[": 110,
|
621 |
+
"\\": 111,
|
622 |
+
"]": 112,
|
623 |
+
"^": 113,
|
624 |
+
"_": 114,
|
625 |
+
"`": 115,
|
626 |
+
"a": 116,
|
627 |
+
"b": 117,
|
628 |
+
"c": 118,
|
629 |
+
"d": 119,
|
630 |
+
"e": 120,
|
631 |
+
"f": 121,
|
632 |
+
"g": 122,
|
633 |
+
"h": 123,
|
634 |
+
"i": 124,
|
635 |
+
"j": 125,
|
636 |
+
"k": 126,
|
637 |
+
"l": 127,
|
638 |
+
"m": 128,
|
639 |
+
"n": 129,
|
640 |
+
"o": 130,
|
641 |
+
"p": 131,
|
642 |
+
"q": 132,
|
643 |
+
"r": 133,
|
644 |
+
"s": 134,
|
645 |
+
"t": 135,
|
646 |
+
"u": 136,
|
647 |
+
"v": 137,
|
648 |
+
"w": 138,
|
649 |
+
"x": 139,
|
650 |
+
"y": 140,
|
651 |
+
"z": 141,
|
652 |
+
"{": 142,
|
653 |
+
"|": 143,
|
654 |
+
"}": 144,
|
655 |
+
"~": 145,
|
656 |
+
"¡": 146,
|
657 |
+
"¢": 147,
|
658 |
+
"£": 148,
|
659 |
+
"¤": 149,
|
660 |
+
"¥": 150,
|
661 |
+
"¦": 151,
|
662 |
+
"§": 152,
|
663 |
+
"©": 153,
|
664 |
+
"¬": 154,
|
665 |
+
"®": 155,
|
666 |
+
"°": 156,
|
667 |
+
"±": 157,
|
668 |
+
"¶": 158,
|
669 |
+
"·": 159,
|
670 |
+
"»": 160,
|
671 |
+
"¿": 161,
|
672 |
+
"À": 162,
|
673 |
+
"Á": 163,
|
674 |
+
"Â": 164,
|
675 |
+
"Ã": 165,
|
676 |
+
"Ä": 166,
|
677 |
+
"Å": 167,
|
678 |
+
"Æ": 168,
|
679 |
+
"Ç": 169,
|
680 |
+
"È": 170,
|
681 |
+
"É": 171,
|
682 |
+
"Ê": 172,
|
683 |
+
"Ë": 173,
|
684 |
+
"Ì": 174,
|
685 |
+
"Í": 175,
|
686 |
+
"Î": 176,
|
687 |
+
"Ï": 177,
|
688 |
+
"Ð": 178,
|
689 |
+
"Ñ": 179,
|
690 |
+
"Ò": 180,
|
691 |
+
"Ó": 181,
|
692 |
+
"Ô": 182,
|
693 |
+
"Õ": 183,
|
694 |
+
"Ö": 184,
|
695 |
+
"×": 185,
|
696 |
+
"Ø": 186,
|
697 |
+
"Ù": 187,
|
698 |
+
"Ú": 188,
|
699 |
+
"Û": 189,
|
700 |
+
"Ü": 190,
|
701 |
+
"Ý": 191,
|
702 |
+
"Þ": 192,
|
703 |
+
"ß": 193,
|
704 |
+
"à": 194,
|
705 |
+
"á": 195,
|
706 |
+
"â": 196,
|
707 |
+
"ã": 197,
|
708 |
+
"ä": 198,
|
709 |
+
"å": 199,
|
710 |
+
"æ": 200,
|
711 |
+
"ç": 201,
|
712 |
+
"è": 202,
|
713 |
+
"é": 203,
|
714 |
+
"ê": 204,
|
715 |
+
"ë": 205,
|
716 |
+
"ì": 206,
|
717 |
+
"í": 207,
|
718 |
+
"î": 208,
|
719 |
+
"ï": 209,
|
720 |
+
"ð": 210,
|
721 |
+
"ñ": 211,
|
722 |
+
"ò": 212,
|
723 |
+
"ó": 213,
|
724 |
+
"ô": 214,
|
725 |
+
"õ": 215,
|
726 |
+
"ö": 216,
|
727 |
+
"÷": 217,
|
728 |
+
"ø": 218,
|
729 |
+
"ù": 219,
|
730 |
+
"ú": 220,
|
731 |
+
"û": 221,
|
732 |
+
"ü": 222,
|
733 |
+
"ý": 223,
|
734 |
+
"þ": 224,
|
735 |
+
"ÿ": 225,
|
736 |
+
"Œ": 226,
|
737 |
+
"œ": 227,
|
738 |
+
"Š": 228,
|
739 |
+
"š": 229,
|
740 |
+
"Ÿ": 230,
|
741 |
+
"Ž": 231,
|
742 |
+
"ž": 232,
|
743 |
+
"ƒ": 233,
|
744 |
+
"ˆ": 234,
|
745 |
+
"́": 235,
|
746 |
+
"̃": 236,
|
747 |
+
"̄": 237,
|
748 |
+
"̈": 238,
|
749 |
+
"̧": 239,
|
750 |
+
"μ": 240,
|
751 |
+
"–": 241,
|
752 |
+
"—": 242,
|
753 |
+
"‚": 243,
|
754 |
+
"“": 244,
|
755 |
+
"”": 245,
|
756 |
+
"„": 246,
|
757 |
+
"†": 247,
|
758 |
+
"‡": 248,
|
759 |
+
"•": 249,
|
760 |
+
"‰": 250,
|
761 |
+
"‹": 251,
|
762 |
+
"›": 252,
|
763 |
+
"⁄": 253,
|
764 |
+
"€": 254,
|
765 |
+
"▁": 255
|
766 |
+
},
|
767 |
+
"merges": []
|
768 |
+
}
|
769 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,436 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "UNKNOWN_0",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "UNKNOWN_1",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "UNKNOWN_2",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "UNKNOWN_3",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "UNKNOWN_4",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "UNKNOWN_5",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "UNKNOWN_6",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "UNKNOWN_7",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"11": {
|
92 |
+
"content": "UNKNOWN_8",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"12": {
|
100 |
+
"content": "UNKNOWN_9",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"13": {
|
108 |
+
"content": "UNKNOWN_10",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"14": {
|
116 |
+
"content": "UNKNOWN_11",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"15": {
|
124 |
+
"content": "UNKNOWN_12",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"16": {
|
132 |
+
"content": "UNKNOWN_13",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"17": {
|
140 |
+
"content": "UNKNOWN_14",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"18": {
|
148 |
+
"content": "UNKNOWN_15",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"19": {
|
156 |
+
"content": "UNKNOWN_16",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"20": {
|
164 |
+
"content": "UNKNOWN_17",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"21": {
|
172 |
+
"content": "UNKNOWN_18",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"22": {
|
180 |
+
"content": "UNKNOWN_19",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"23": {
|
188 |
+
"content": "UNKNOWN_20",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"24": {
|
196 |
+
"content": "UNKNOWN_21",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"25": {
|
204 |
+
"content": "UNKNOWN_22",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"26": {
|
212 |
+
"content": "UNKNOWN_23",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"27": {
|
220 |
+
"content": "UNKNOWN_24",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"28": {
|
228 |
+
"content": "UNKNOWN_25",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"29": {
|
236 |
+
"content": "UNKNOWN_26",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"30": {
|
244 |
+
"content": "UNKNOWN_27",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"31": {
|
252 |
+
"content": "UNKNOWN_28",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"32": {
|
260 |
+
"content": "UNKNOWN_29",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"33": {
|
268 |
+
"content": "UNKNOWN_30",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"34": {
|
276 |
+
"content": "UNKNOWN_31",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"35": {
|
284 |
+
"content": "UNKNOWN_32",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"36": {
|
292 |
+
"content": "UNKNOWN_33",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"37": {
|
300 |
+
"content": "UNKNOWN_34",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"38": {
|
308 |
+
"content": "UNKNOWN_35",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"39": {
|
316 |
+
"content": "UNKNOWN_36",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"40": {
|
324 |
+
"content": "UNKNOWN_37",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"41": {
|
332 |
+
"content": "UNKNOWN_38",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"42": {
|
340 |
+
"content": "UNKNOWN_39",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"43": {
|
348 |
+
"content": "UNKNOWN_40",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"44": {
|
356 |
+
"content": "UNKNOWN_41",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"45": {
|
364 |
+
"content": "UNKNOWN_42",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"46": {
|
372 |
+
"content": "UNKNOWN_43",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"47": {
|
380 |
+
"content": "UNKNOWN_44",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"48": {
|
388 |
+
"content": "UNKNOWN_45",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"49": {
|
396 |
+
"content": "UNKNOWN_46",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"50": {
|
404 |
+
"content": "UNKNOWN_47",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"51": {
|
412 |
+
"content": "UNKNOWN_48",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"52": {
|
420 |
+
"content": "UNKNOWN_49",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
}
|
427 |
+
},
|
428 |
+
"clean_up_tokenization_spaces": true,
|
429 |
+
"model_input_names": [
|
430 |
+
"input_ids",
|
431 |
+
"attention_mask"
|
432 |
+
],
|
433 |
+
"model_max_length": 256,
|
434 |
+
"special_tokens": null,
|
435 |
+
"tokenizer_class": "LlamaTokenizer"
|
436 |
+
}
|