Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +1 -1
- tokenizer_config.json +3 -3
special_tokens_map.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"content": "<|placeholder6|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
-
"rstrip":
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
|
|
|
| 17 |
"content": "<|placeholder6|>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"unk_token": {
|
tokenizer.json
CHANGED
|
@@ -116,7 +116,7 @@
|
|
| 116 |
"content": "<|placeholder6|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
-
"rstrip":
|
| 120 |
"normalized": false,
|
| 121 |
"special": true
|
| 122 |
},
|
|
|
|
| 116 |
"content": "<|placeholder6|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
"normalized": false,
|
| 121 |
"special": true
|
| 122 |
},
|
tokenizer_config.json
CHANGED
|
@@ -103,7 +103,7 @@
|
|
| 103 |
"content": "<|placeholder6|>",
|
| 104 |
"lstrip": false,
|
| 105 |
"normalized": false,
|
| 106 |
-
"rstrip":
|
| 107 |
"single_word": false,
|
| 108 |
"special": true
|
| 109 |
},
|
|
@@ -117,10 +117,10 @@
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<s>",
|
| 120 |
-
"chat_template": "{% for message in messages %}{% if
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
-
"legacy":
|
| 124 |
"model_max_length": 4096,
|
| 125 |
"pad_token": "<|placeholder6|>",
|
| 126 |
"padding_side": "left",
|
|
|
|
| 103 |
"content": "<|placeholder6|>",
|
| 104 |
"lstrip": false,
|
| 105 |
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
"single_word": false,
|
| 108 |
"special": true
|
| 109 |
},
|
|
|
|
| 117 |
}
|
| 118 |
},
|
| 119 |
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if 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,
|
| 124 |
"model_max_length": 4096,
|
| 125 |
"pad_token": "<|placeholder6|>",
|
| 126 |
"padding_side": "left",
|