Commit
•
00dd341
1
Parent(s):
ad636d9
Upload processor
Browse files- special_tokens_map.json +28 -3
- tokenizer_config.json +2 -0
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
}
|
tokenizer_config.json
CHANGED
|
@@ -8005,6 +8005,8 @@
|
|
| 8005 |
"clean_up_tokenization_spaces": false,
|
| 8006 |
"eos_token": "</s>",
|
| 8007 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
| 8008 |
"processor_class": "PixtralProcessor",
|
| 8009 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8010 |
"unk_token": "<unk>"
|
|
|
|
| 8005 |
"clean_up_tokenization_spaces": false,
|
| 8006 |
"eos_token": "</s>",
|
| 8007 |
"model_max_length": 1000000000000000019884624838656,
|
| 8008 |
+
"pad_token": "<pad>",
|
| 8009 |
+
"padding_side": "left",
|
| 8010 |
"processor_class": "PixtralProcessor",
|
| 8011 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8012 |
"unk_token": "<unk>"
|