Upload tokenizer
Browse files- tokenizer.json +0 -27
- tokenizer_config.json +3 -2
tokenizer.json
CHANGED
|
@@ -62,12 +62,6 @@
|
|
| 62 |
"id": "A",
|
| 63 |
"type_id": 0
|
| 64 |
}
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"SpecialToken": {
|
| 68 |
-
"id": "</s>",
|
| 69 |
-
"type_id": 0
|
| 70 |
-
}
|
| 71 |
}
|
| 72 |
],
|
| 73 |
"pair": [
|
|
@@ -83,12 +77,6 @@
|
|
| 83 |
"type_id": 0
|
| 84 |
}
|
| 85 |
},
|
| 86 |
-
{
|
| 87 |
-
"SpecialToken": {
|
| 88 |
-
"id": "</s>",
|
| 89 |
-
"type_id": 0
|
| 90 |
-
}
|
| 91 |
-
},
|
| 92 |
{
|
| 93 |
"SpecialToken": {
|
| 94 |
"id": "<s>",
|
|
@@ -100,24 +88,9 @@
|
|
| 100 |
"id": "B",
|
| 101 |
"type_id": 1
|
| 102 |
}
|
| 103 |
-
},
|
| 104 |
-
{
|
| 105 |
-
"SpecialToken": {
|
| 106 |
-
"id": "</s>",
|
| 107 |
-
"type_id": 1
|
| 108 |
-
}
|
| 109 |
}
|
| 110 |
],
|
| 111 |
"special_tokens": {
|
| 112 |
-
"</s>": {
|
| 113 |
-
"id": "</s>",
|
| 114 |
-
"ids": [
|
| 115 |
-
2
|
| 116 |
-
],
|
| 117 |
-
"tokens": [
|
| 118 |
-
"</s>"
|
| 119 |
-
]
|
| 120 |
-
},
|
| 121 |
"<s>": {
|
| 122 |
"id": "<s>",
|
| 123 |
"ids": [
|
|
|
|
| 62 |
"id": "A",
|
| 63 |
"type_id": 0
|
| 64 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
}
|
| 66 |
],
|
| 67 |
"pair": [
|
|
|
|
| 77 |
"type_id": 0
|
| 78 |
}
|
| 79 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
{
|
| 81 |
"SpecialToken": {
|
| 82 |
"id": "<s>",
|
|
|
|
| 88 |
"id": "B",
|
| 89 |
"type_id": 1
|
| 90 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
"<s>": {
|
| 95 |
"id": "<s>",
|
| 96 |
"ids": [
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
-
"add_eos_token":
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -29,9 +29,10 @@
|
|
| 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
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
|
|
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
"pad_token": "</s>",
|
| 37 |
"sp_model_kwargs": {},
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 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": {},
|