Commit
•
37f529e
1
Parent(s):
0ad0627
Upload tokenizer (#13)
Browse files- Upload tokenizer (3cbf8c491be07fa369a42dce3daa25ad17f32e97)
- special_tokens_map.json +4 -4
- tokenizer.json +0 -0
- tokenizer_config.json +5 -9
special_tokens_map.json
CHANGED
|
@@ -1,21 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
-
"content": "",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": true,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": true,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "
|
| 17 |
"unk_token": {
|
| 18 |
-
"content": "",
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": true,
|
| 21 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": true,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": true,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": true,
|
| 21 |
"rstrip": false,
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,9 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"bos_token": {
|
| 5 |
"__type": "AddedToken",
|
| 6 |
-
"content": "",
|
| 7 |
"lstrip": false,
|
| 8 |
"normalized": true,
|
| 9 |
"rstrip": false,
|
|
@@ -12,25 +10,23 @@
|
|
| 12 |
"clean_up_tokenization_spaces": false,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
-
"content": "",
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": true,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
-
"legacy":
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": null,
|
| 24 |
"sp_model_kwargs": {},
|
| 25 |
-
"spaces_between_special_tokens": false,
|
| 26 |
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
"unk_token": {
|
| 28 |
"__type": "AddedToken",
|
| 29 |
-
"content": "",
|
| 30 |
"lstrip": false,
|
| 31 |
"normalized": true,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
-
}
|
| 35 |
-
"use_default_system_prompt": true
|
| 36 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": true,
|
| 7 |
"rstrip": false,
|
|
|
|
| 10 |
"clean_up_tokenization_spaces": false,
|
| 11 |
"eos_token": {
|
| 12 |
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
"lstrip": false,
|
| 15 |
"normalized": true,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
| 19 |
+
"legacy": false,
|
| 20 |
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
"pad_token": null,
|
| 22 |
"sp_model_kwargs": {},
|
|
|
|
| 23 |
"tokenizer_class": "LlamaTokenizer",
|
| 24 |
"unk_token": {
|
| 25 |
"__type": "AddedToken",
|
| 26 |
+
"content": "<unk>",
|
| 27 |
"lstrip": false,
|
| 28 |
"normalized": true,
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
+
}
|
|
|
|
| 32 |
}
|