Upload tokenizer_config.json
Browse files- tokenizer_config.json +77 -142
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_eos_token": false,
|
4 |
"add_prefix_space": false,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
@@ -12,223 +10,159 @@
|
|
12 |
"special": true
|
13 |
},
|
14 |
"1": {
|
15 |
-
"content": "
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
"special": true
|
21 |
},
|
22 |
-
"
|
23 |
-
"content": "
|
24 |
"lstrip": false,
|
25 |
-
"normalized":
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": false
|
29 |
-
},
|
30 |
-
"50255": {
|
31 |
-
"content": " ",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": false
|
37 |
-
},
|
38 |
-
"50256": {
|
39 |
-
"content": " ",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": true,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false,
|
44 |
-
"special": false
|
45 |
-
},
|
46 |
-
"50257": {
|
47 |
-
"content": " ",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": true,
|
50 |
-
"rstrip": false,
|
51 |
-
"single_word": false,
|
52 |
-
"special": false
|
53 |
-
},
|
54 |
-
"50258": {
|
55 |
-
"content": " ",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": true,
|
58 |
-
"rstrip": false,
|
59 |
-
"single_word": false,
|
60 |
-
"special": false
|
61 |
-
},
|
62 |
-
"50259": {
|
63 |
-
"content": " ",
|
64 |
-
"lstrip": false,
|
65 |
-
"normalized": true,
|
66 |
-
"rstrip": false,
|
67 |
-
"single_word": false,
|
68 |
-
"special": false
|
69 |
-
},
|
70 |
-
"50260": {
|
71 |
-
"content": " ",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": true,
|
74 |
-
"rstrip": false,
|
75 |
-
"single_word": false,
|
76 |
-
"special": false
|
77 |
-
},
|
78 |
-
"50261": {
|
79 |
-
"content": " ",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": true,
|
82 |
-
"rstrip": false,
|
83 |
-
"single_word": false,
|
84 |
-
"special": false
|
85 |
-
},
|
86 |
-
"50262": {
|
87 |
-
"content": " ",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": true,
|
90 |
"rstrip": false,
|
91 |
"single_word": false,
|
92 |
-
"special":
|
93 |
},
|
94 |
-
"
|
95 |
-
"content": "
|
96 |
"lstrip": false,
|
97 |
-
"normalized":
|
98 |
"rstrip": false,
|
99 |
"single_word": false,
|
100 |
-
"special":
|
101 |
},
|
102 |
-
"
|
103 |
-
"content": "
|
104 |
"lstrip": false,
|
105 |
-
"normalized":
|
106 |
"rstrip": false,
|
107 |
"single_word": false,
|
108 |
-
"special":
|
109 |
},
|
110 |
-
"
|
111 |
-
"content": "
|
112 |
"lstrip": false,
|
113 |
-
"normalized":
|
114 |
"rstrip": false,
|
115 |
"single_word": false,
|
116 |
-
"special":
|
117 |
},
|
118 |
-
"
|
119 |
-
"content": "
|
120 |
"lstrip": false,
|
121 |
-
"normalized":
|
122 |
"rstrip": false,
|
123 |
"single_word": false,
|
124 |
-
"special":
|
125 |
},
|
126 |
-
"
|
127 |
-
"content": "
|
128 |
"lstrip": false,
|
129 |
-
"normalized":
|
130 |
"rstrip": false,
|
131 |
"single_word": false,
|
132 |
-
"special":
|
133 |
},
|
134 |
-
"
|
135 |
-
"content": "
|
136 |
"lstrip": false,
|
137 |
-
"normalized":
|
138 |
"rstrip": false,
|
139 |
"single_word": false,
|
140 |
-
"special":
|
141 |
},
|
142 |
-
"
|
143 |
-
"content": "
|
144 |
"lstrip": false,
|
145 |
-
"normalized":
|
146 |
"rstrip": false,
|
147 |
"single_word": false,
|
148 |
-
"special":
|
149 |
},
|
150 |
-
"
|
151 |
-
"content": "
|
152 |
"lstrip": false,
|
153 |
-
"normalized":
|
154 |
"rstrip": false,
|
155 |
"single_word": false,
|
156 |
-
"special":
|
157 |
},
|
158 |
-
"
|
159 |
-
"content": "
|
160 |
"lstrip": false,
|
161 |
-
"normalized":
|
162 |
"rstrip": false,
|
163 |
"single_word": false,
|
164 |
-
"special":
|
165 |
},
|
166 |
-
"
|
167 |
-
"content": "
|
168 |
"lstrip": false,
|
169 |
-
"normalized":
|
170 |
"rstrip": false,
|
171 |
"single_word": false,
|
172 |
-
"special":
|
173 |
},
|
174 |
-
"
|
175 |
-
"content": "
|
176 |
"lstrip": false,
|
177 |
-
"normalized":
|
178 |
"rstrip": false,
|
179 |
"single_word": false,
|
180 |
-
"special":
|
181 |
},
|
182 |
-
"
|
183 |
-
"content": "
|
184 |
"lstrip": false,
|
185 |
-
"normalized":
|
186 |
"rstrip": false,
|
187 |
"single_word": false,
|
188 |
-
"special":
|
189 |
},
|
190 |
-
"
|
191 |
-
"content": "
|
192 |
"lstrip": false,
|
193 |
-
"normalized":
|
194 |
"rstrip": false,
|
195 |
"single_word": false,
|
196 |
-
"special":
|
197 |
},
|
198 |
-
"
|
199 |
-
"content": "
|
200 |
"lstrip": false,
|
201 |
-
"normalized":
|
202 |
"rstrip": false,
|
203 |
"single_word": false,
|
204 |
-
"special":
|
205 |
},
|
206 |
-
"
|
207 |
-
"content": "
|
208 |
"lstrip": false,
|
209 |
-
"normalized":
|
210 |
"rstrip": false,
|
211 |
"single_word": false,
|
212 |
-
"special":
|
213 |
},
|
214 |
-
"
|
215 |
-
"content": "
|
216 |
"lstrip": false,
|
217 |
"normalized": false,
|
218 |
"rstrip": false,
|
219 |
"single_word": false,
|
220 |
"special": true
|
221 |
},
|
222 |
-
"
|
223 |
-
"content": "<|
|
224 |
"lstrip": false,
|
225 |
"normalized": false,
|
226 |
"rstrip": false,
|
227 |
"single_word": false,
|
228 |
"special": true
|
229 |
},
|
230 |
-
"
|
231 |
-
"content": "
|
232 |
"lstrip": false,
|
233 |
"normalized": false,
|
234 |
"rstrip": false,
|
@@ -240,13 +174,14 @@
|
|
240 |
"<|im_start|>",
|
241 |
"<|im_end|>"
|
242 |
],
|
243 |
-
"bos_token": "<|
|
244 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
245 |
"clean_up_tokenization_spaces": true,
|
246 |
-
"eos_token": "<|
|
247 |
-
"model_max_length":
|
248 |
-
"pad_token": "<|
|
249 |
-
"
|
|
|
250 |
"unk_token": "<|endoftext|>",
|
251 |
"vocab_size": 49152
|
252 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
|
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
+
"content": "<fim_prefix>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
+
"content": "<fim_middle>",
|
22 |
"lstrip": false,
|
23 |
+
"normalized": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"rstrip": false,
|
25 |
"single_word": false,
|
26 |
+
"special": true
|
27 |
},
|
28 |
+
"3": {
|
29 |
+
"content": "<fim_suffix>",
|
30 |
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
"rstrip": false,
|
33 |
"single_word": false,
|
34 |
+
"special": true
|
35 |
},
|
36 |
+
"4": {
|
37 |
+
"content": "<fim_pad>",
|
38 |
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
+
"special": true
|
43 |
},
|
44 |
+
"5": {
|
45 |
+
"content": "<filename>",
|
46 |
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
"rstrip": false,
|
49 |
"single_word": false,
|
50 |
+
"special": true
|
51 |
},
|
52 |
+
"6": {
|
53 |
+
"content": "<gh_stars>",
|
54 |
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
"rstrip": false,
|
57 |
"single_word": false,
|
58 |
+
"special": true
|
59 |
},
|
60 |
+
"7": {
|
61 |
+
"content": "<issue_start>",
|
62 |
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
"rstrip": false,
|
65 |
"single_word": false,
|
66 |
+
"special": true
|
67 |
},
|
68 |
+
"8": {
|
69 |
+
"content": "<issue_comment>",
|
70 |
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
"rstrip": false,
|
73 |
"single_word": false,
|
74 |
+
"special": true
|
75 |
},
|
76 |
+
"9": {
|
77 |
+
"content": "<issue_closed>",
|
78 |
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
"rstrip": false,
|
81 |
"single_word": false,
|
82 |
+
"special": true
|
83 |
},
|
84 |
+
"10": {
|
85 |
+
"content": "<jupyter_start>",
|
86 |
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
"rstrip": false,
|
89 |
"single_word": false,
|
90 |
+
"special": true
|
91 |
},
|
92 |
+
"11": {
|
93 |
+
"content": "<jupyter_text>",
|
94 |
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
"rstrip": false,
|
97 |
"single_word": false,
|
98 |
+
"special": true
|
99 |
},
|
100 |
+
"12": {
|
101 |
+
"content": "<jupyter_code>",
|
102 |
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
"rstrip": false,
|
105 |
"single_word": false,
|
106 |
+
"special": true
|
107 |
},
|
108 |
+
"13": {
|
109 |
+
"content": "<jupyter_output>",
|
110 |
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
"rstrip": false,
|
113 |
"single_word": false,
|
114 |
+
"special": true
|
115 |
},
|
116 |
+
"14": {
|
117 |
+
"content": "<empty_output>",
|
118 |
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
"rstrip": false,
|
121 |
"single_word": false,
|
122 |
+
"special": true
|
123 |
},
|
124 |
+
"15": {
|
125 |
+
"content": "<commit_before>",
|
126 |
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
"rstrip": false,
|
129 |
"single_word": false,
|
130 |
+
"special": true
|
131 |
},
|
132 |
+
"16": {
|
133 |
+
"content": "<commit_msg>",
|
134 |
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
"rstrip": false,
|
137 |
"single_word": false,
|
138 |
+
"special": true
|
139 |
},
|
140 |
+
"17": {
|
141 |
+
"content": "<commit_after>",
|
142 |
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
"rstrip": false,
|
145 |
"single_word": false,
|
146 |
+
"special": true
|
147 |
},
|
148 |
+
"18": {
|
149 |
+
"content": "<reponame>",
|
150 |
"lstrip": false,
|
151 |
"normalized": false,
|
152 |
"rstrip": false,
|
153 |
"single_word": false,
|
154 |
"special": true
|
155 |
},
|
156 |
+
"49152": {
|
157 |
+
"content": "<|im_start|>",
|
158 |
"lstrip": false,
|
159 |
"normalized": false,
|
160 |
"rstrip": false,
|
161 |
"single_word": false,
|
162 |
"special": true
|
163 |
},
|
164 |
+
"49153": {
|
165 |
+
"content": "<|im_end|>",
|
166 |
"lstrip": false,
|
167 |
"normalized": false,
|
168 |
"rstrip": false,
|
|
|
174 |
"<|im_start|>",
|
175 |
"<|im_end|>"
|
176 |
],
|
177 |
+
"bos_token": "<|endoftext|>",
|
178 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
179 |
"clean_up_tokenization_spaces": true,
|
180 |
+
"eos_token": "<|endoftext|>",
|
181 |
+
"model_max_length": 9223372036854775807,
|
182 |
+
"pad_token": "<|endoftext|>",
|
183 |
+
"padding_side": "left",
|
184 |
+
"tokenizer_class": "GPT2Tokenizer",
|
185 |
"unk_token": "<|endoftext|>",
|
186 |
"vocab_size": 49152
|
187 |
}
|