Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +16 -2
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 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": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Left",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 2,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "</s>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": true,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
-
"pad_token":
|
| 36 |
"sp_model_kwargs": {},
|
| 37 |
"spaces_between_special_tokens": false,
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": true,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
"sp_model_kwargs": {},
|
| 37 |
"spaces_between_special_tokens": false,
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|