Update tokenizer_config.json
Browse files- tokenizer_config.json +6 -4
tokenizer_config.json
CHANGED
|
@@ -145,7 +145,7 @@
|
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
"128018": {
|
| 148 |
-
"content": "<|
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
| 151 |
"rstrip": false,
|
|
@@ -153,7 +153,7 @@
|
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
"128019": {
|
| 156 |
-
"content": "<|
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
| 159 |
"rstrip": false,
|
|
@@ -2050,12 +2050,14 @@
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
-
"eos_token": "<|
|
| 2055 |
"model_input_names": [
|
| 2056 |
"input_ids",
|
| 2057 |
"attention_mask"
|
| 2058 |
],
|
| 2059 |
"model_max_length": 131072,
|
|
|
|
| 2060 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2061 |
-
}
|
|
|
|
| 145 |
"special": true
|
| 146 |
},
|
| 147 |
"128018": {
|
| 148 |
+
"content": "<|im_start|>",
|
| 149 |
"lstrip": false,
|
| 150 |
"normalized": false,
|
| 151 |
"rstrip": false,
|
|
|
|
| 153 |
"special": true
|
| 154 |
},
|
| 155 |
"128019": {
|
| 156 |
+
"content": "<|im_end|>",
|
| 157 |
"lstrip": false,
|
| 158 |
"normalized": false,
|
| 159 |
"rstrip": false,
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|im_end|>",
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2063 |
+
}
|