Upload tokenizer
Browse files- special_tokens_map.json +1 -6
- tokenizer_config.json +3 -9
special_tokens_map.json
CHANGED
|
@@ -1,9 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<unk>",
|
| 4 |
-
"<s>",
|
| 5 |
-
"</s>"
|
| 6 |
-
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<s>",
|
| 9 |
"lstrip": false,
|
|
@@ -19,7 +14,7 @@
|
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"pad_token": {
|
| 22 |
-
"content": "
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -27,11 +27,7 @@
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"additional_special_tokens": [
|
| 31 |
-
"<unk>",
|
| 32 |
-
"<s>",
|
| 33 |
-
"</s>"
|
| 34 |
-
],
|
| 35 |
"bos_token": "<s>",
|
| 36 |
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 37 |
"clean_up_tokenization_spaces": false,
|
|
@@ -39,15 +35,13 @@
|
|
| 39 |
"legacy": true,
|
| 40 |
"max_length": 2048,
|
| 41 |
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
-
"pad_token": "
|
| 43 |
"sp_model_kwargs": {},
|
| 44 |
"spaces_between_special_tokens": false,
|
| 45 |
"stride": 0,
|
| 46 |
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
"truncation_side": "right",
|
| 48 |
"truncation_strategy": "longest_first",
|
| 49 |
-
"trust_remote_code": false,
|
| 50 |
"unk_token": "<unk>",
|
| 51 |
-
"use_default_system_prompt": false
|
| 52 |
-
"use_fast": true
|
| 53 |
}
|
|
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 33 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 35 |
"legacy": true,
|
| 36 |
"max_length": 2048,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": "<unk>",
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"stride": 0,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
"truncation_side": "right",
|
| 44 |
"truncation_strategy": "longest_first",
|
|
|
|
| 45 |
"unk_token": "<unk>",
|
| 46 |
+
"use_default_system_prompt": false
|
|
|
|
| 47 |
}
|