Upload tokenizer
Browse files- special_tokens_map.json +7 -2
- tokenizer_config.json +3 -2
special_tokens_map.json
CHANGED
@@ -6,8 +6,13 @@
|
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"eos_token":
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
11 |
"unk_token": {
|
12 |
"content": "<unk>",
|
13 |
"lstrip": false,
|
|
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -29,11 +29,12 @@
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
-
"eos_token": "
|
34 |
"legacy": true,
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% set loop_messages = messages %}\n{% for message in loop_messages %}\n{% set content = message['role']+'\n'+ message['content'] + '\n' %}\n{% if message['role'] == 'System' %}\n{% set content = '<extra_id_0>' + content %}\n{% else %}\n{% set content = '<extra_id_1>' + content %}\n{% endif %}\n{{ content }}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ '<extra_id_1>Assistant' }}\n\n{% endif %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": null,
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|