Upload tokenizer
Browse files- tokenizer.json +0 -27
- tokenizer_config.json +2 -2
tokenizer.json
CHANGED
|
@@ -155,12 +155,6 @@
|
|
| 155 |
"post_processor": {
|
| 156 |
"type": "TemplateProcessing",
|
| 157 |
"single": [
|
| 158 |
-
{
|
| 159 |
-
"SpecialToken": {
|
| 160 |
-
"id": "<s>",
|
| 161 |
-
"type_id": 0
|
| 162 |
-
}
|
| 163 |
-
},
|
| 164 |
{
|
| 165 |
"Sequence": {
|
| 166 |
"id": "A",
|
|
@@ -175,12 +169,6 @@
|
|
| 175 |
}
|
| 176 |
],
|
| 177 |
"pair": [
|
| 178 |
-
{
|
| 179 |
-
"SpecialToken": {
|
| 180 |
-
"id": "<s>",
|
| 181 |
-
"type_id": 0
|
| 182 |
-
}
|
| 183 |
-
},
|
| 184 |
{
|
| 185 |
"Sequence": {
|
| 186 |
"id": "A",
|
|
@@ -193,12 +181,6 @@
|
|
| 193 |
"type_id": 0
|
| 194 |
}
|
| 195 |
},
|
| 196 |
-
{
|
| 197 |
-
"SpecialToken": {
|
| 198 |
-
"id": "<s>",
|
| 199 |
-
"type_id": 1
|
| 200 |
-
}
|
| 201 |
-
},
|
| 202 |
{
|
| 203 |
"Sequence": {
|
| 204 |
"id": "B",
|
|
@@ -213,15 +195,6 @@
|
|
| 213 |
}
|
| 214 |
],
|
| 215 |
"special_tokens": {
|
| 216 |
-
"<s>": {
|
| 217 |
-
"id": "<s>",
|
| 218 |
-
"ids": [
|
| 219 |
-
1
|
| 220 |
-
],
|
| 221 |
-
"tokens": [
|
| 222 |
-
"<s>"
|
| 223 |
-
]
|
| 224 |
-
},
|
| 225 |
"<|endoftext|>": {
|
| 226 |
"id": "<|endoftext|>",
|
| 227 |
"ids": [
|
|
|
|
| 155 |
"post_processor": {
|
| 156 |
"type": "TemplateProcessing",
|
| 157 |
"single": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
{
|
| 159 |
"Sequence": {
|
| 160 |
"id": "A",
|
|
|
|
| 169 |
}
|
| 170 |
],
|
| 171 |
"pair": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 172 |
{
|
| 173 |
"Sequence": {
|
| 174 |
"id": "A",
|
|
|
|
| 181 |
"type_id": 0
|
| 182 |
}
|
| 183 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
{
|
| 185 |
"Sequence": {
|
| 186 |
"id": "B",
|
|
|
|
| 195 |
}
|
| 196 |
],
|
| 197 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
"<|endoftext|>": {
|
| 199 |
"id": "<|endoftext|>",
|
| 200 |
"ids": [
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token":
|
| 3 |
"add_eos_token": true,
|
| 4 |
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
|
@@ -117,7 +117,7 @@
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<s>",
|
| 120 |
-
"chat_template": "{
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"legacy": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
"add_eos_token": true,
|
| 4 |
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
|
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"legacy": false,
|