Upload 3 files
Browse files- tokenizer.json +1 -18
- tokenizer_config.json +1 -17
tokenizer.json
CHANGED
@@ -173,24 +173,6 @@
|
|
173 |
"rstrip": false,
|
174 |
"normalized": false,
|
175 |
"special": true
|
176 |
-
},
|
177 |
-
{
|
178 |
-
"id": 49152,
|
179 |
-
"content": "<|im_start|>",
|
180 |
-
"single_word": false,
|
181 |
-
"lstrip": false,
|
182 |
-
"rstrip": false,
|
183 |
-
"normalized": false,
|
184 |
-
"special": true
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"id": 49153,
|
188 |
-
"content": "<|im_end|>",
|
189 |
-
"single_word": false,
|
190 |
-
"lstrip": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"normalized": false,
|
193 |
-
"special": true
|
194 |
}
|
195 |
],
|
196 |
"normalizer": null,
|
@@ -224,6 +206,7 @@
|
|
224 |
"end_of_word_suffix": null,
|
225 |
"fuse_unk": false,
|
226 |
"byte_fallback": false,
|
|
|
227 |
"vocab": {
|
228 |
"<|endoftext|>": 0,
|
229 |
"<fim_prefix>": 1,
|
|
|
173 |
"rstrip": false,
|
174 |
"normalized": false,
|
175 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
176 |
}
|
177 |
],
|
178 |
"normalizer": null,
|
|
|
206 |
"end_of_word_suffix": null,
|
207 |
"fuse_unk": false,
|
208 |
"byte_fallback": false,
|
209 |
+
"ignore_merges": false,
|
210 |
"vocab": {
|
211 |
"<|endoftext|>": 0,
|
212 |
"<fim_prefix>": 1,
|
tokenizer_config.json
CHANGED
@@ -152,22 +152,6 @@
|
|
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,
|
169 |
-
"single_word": false,
|
170 |
-
"special": true
|
171 |
}
|
172 |
},
|
173 |
"additional_special_tokens": [
|
@@ -192,7 +176,7 @@
|
|
192 |
"<reponame>"
|
193 |
],
|
194 |
"bos_token": "<|endoftext|>",
|
195 |
-
"chat_template": "{% for message in messages %}{{'
|
196 |
"clean_up_tokenization_spaces": true,
|
197 |
"eos_token": "<|endoftext|>",
|
198 |
"model_max_length": 9223372036854775807,
|
|
|
152 |
"rstrip": false,
|
153 |
"single_word": false,
|
154 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
155 |
}
|
156 |
},
|
157 |
"additional_special_tokens": [
|
|
|
176 |
"<reponame>"
|
177 |
],
|
178 |
"bos_token": "<|endoftext|>",
|
179 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'Question:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'system' %}\n{{ 'System:\n' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Answer:\n' + message['content'] + '\n\n' }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Answer:\n' }}{% endif %}{% endfor %}",
|
180 |
"clean_up_tokenization_spaces": true,
|
181 |
"eos_token": "<|endoftext|>",
|
182 |
"model_max_length": 9223372036854775807,
|