Upload tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer_config.json +7 -2
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<s>",
|
| 9 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -27,16 +27,21 @@
|
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
},
|
| 30 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"legacy": true,
|
| 35 |
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
"pad_token": "</s>",
|
|
|
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
"unk_token": "<unk>",
|
| 41 |
-
"use_default_system_prompt":
|
| 42 |
}
|
|
|
|
| 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",
|
| 45 |
"unk_token": "<unk>",
|
| 46 |
+
"use_default_system_prompt": true
|
| 47 |
}
|