Upload 5 files
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +2 -2
- tokenizer_config.json +3 -1
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -41,7 +41,7 @@
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
-
"content": "
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
@@ -9107,7 +9107,7 @@
|
|
| 9107 |
"<s>": 1,
|
| 9108 |
"<|im_end|>": 2,
|
| 9109 |
"<|im_start|>": 3,
|
| 9110 |
-
"
|
| 9111 |
"[AVAILABLE_TOOLS]": 5,
|
| 9112 |
"[/AVAILABLE_TOOLS]": 6,
|
| 9113 |
"[TOOL_RESULTS]": 7,
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
+
"content": "<SPECIAL_4>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 9107 |
"<s>": 1,
|
| 9108 |
"<|im_end|>": 2,
|
| 9109 |
"<|im_start|>": 3,
|
| 9110 |
+
"<SPECIAL_4>": 4,
|
| 9111 |
"[AVAILABLE_TOOLS]": 5,
|
| 9112 |
"[/AVAILABLE_TOOLS]": 6,
|
| 9113 |
"[TOOL_RESULTS]": 7,
|
tokenizer_config.json
CHANGED
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"special": true
|
| 37 |
},
|
| 38 |
"4": {
|
| 39 |
-
"content": "
|
| 40 |
"lstrip": false,
|
| 41 |
"normalized": false,
|
| 42 |
"rstrip": false,
|
|
@@ -8005,9 +8005,11 @@
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
|
|
|
| 8008 |
"clean_up_tokenization_spaces": false,
|
| 8009 |
"eos_token": "<|im_end|>",
|
| 8010 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 8011 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8012 |
"unk_token": "<unk>"
|
| 8013 |
}
|
|
|
|
| 36 |
"special": true
|
| 37 |
},
|
| 38 |
"4": {
|
| 39 |
+
"content": "<SPECIAL_14>",
|
| 40 |
"lstrip": false,
|
| 41 |
"normalized": false,
|
| 42 |
"rstrip": false,
|
|
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
| 8008 |
+
"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 %}",
|
| 8009 |
"clean_up_tokenization_spaces": false,
|
| 8010 |
"eos_token": "<|im_end|>",
|
| 8011 |
"model_max_length": 1000000000000000019884624838656,
|
| 8012 |
+
"pad_token": "<pad>",
|
| 8013 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8014 |
"unk_token": "<unk>"
|
| 8015 |
}
|