Upload tokenizer
Browse files- special_tokens_map.json +21 -4
- tokenizer_config.json +1 -2
special_tokens_map.json
CHANGED
@@ -1,6 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": 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,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -25,14 +25,13 @@
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
-
"additional_special_tokens": [],
|
29 |
"bos_token": "<s>",
|
30 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
-
"pad_token":
|
36 |
"padding_side": "right",
|
37 |
"sp_model_kwargs": {},
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
|
|
28 |
"bos_token": "<s>",
|
29 |
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": false,
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": null,
|
35 |
"padding_side": "right",
|
36 |
"sp_model_kwargs": {},
|
37 |
"tokenizer_class": "LlamaTokenizer",
|