Upload 4 files
Browse files- special_tokens_map.json +6 -1
- tokenizer.json +0 -0
- tokenizer_config.json +3 -4
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,9 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<s>",
|
| 4 |
"lstrip": false,
|
|
@@ -14,7 +19,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<s>",
|
| 9 |
"lstrip": false,
|
|
|
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
"lstrip": false,
|
| 24 |
"normalized": false,
|
| 25 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -34,12 +34,11 @@
|
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
"legacy": false,
|
| 37 |
-
"model_max_length":
|
| 38 |
-
"pad_token":
|
| 39 |
-
"padding_side": "left",
|
| 40 |
"sp_model_kwargs": {},
|
| 41 |
"spaces_between_special_tokens": false,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
"unk_token": "<unk>",
|
| 44 |
"use_default_system_prompt": false
|
| 45 |
-
}
|
|
|
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
"legacy": false,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": null,
|
|
|
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": false
|
| 44 |
+
}
|