Upload tokenizer
Browse files- special_tokens_map.json +0 -5
- tokenizer.json +14 -2
- tokenizer_config.json +2 -6
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,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": "BatchLongest",
|
| 11 |
+
"direction": "Left",
|
| 12 |
+
"pad_to_multiple_of": null,
|
| 13 |
+
"pad_id": 2,
|
| 14 |
+
"pad_type_id": 0,
|
| 15 |
+
"pad_token": "</s>"
|
| 16 |
+
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -27,18 +27,14 @@
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"additional_special_tokens": [
|
| 31 |
-
"<unk>",
|
| 32 |
-
"<s>",
|
| 33 |
-
"</s>"
|
| 34 |
-
],
|
| 35 |
"bos_token": "<s>",
|
|
|
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
"eos_token": "</s>",
|
| 38 |
"legacy": true,
|
| 39 |
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
"pad_token": "</s>",
|
| 41 |
-
"padding_side": "left",
|
| 42 |
"sp_model_kwargs": {},
|
| 43 |
"spaces_between_special_tokens": false,
|
| 44 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 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,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"legacy": true,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": "</s>",
|
|
|
|
| 38 |
"sp_model_kwargs": {},
|
| 39 |
"spaces_between_special_tokens": false,
|
| 40 |
"tokenizer_class": "LlamaTokenizer",
|