Upload folder using huggingface_hub
Browse files- tokenizer.json +26 -1
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
@@ -47,7 +47,32 @@
|
|
| 47 |
"prepend_scheme": "first",
|
| 48 |
"split": false
|
| 49 |
},
|
| 50 |
-
"post_processor":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"decoder": {
|
| 52 |
"type": "Sequence",
|
| 53 |
"decoders": [
|
|
|
|
| 47 |
"prepend_scheme": "first",
|
| 48 |
"split": false
|
| 49 |
},
|
| 50 |
+
"post_processor": {
|
| 51 |
+
"type": "TemplateProcessing",
|
| 52 |
+
"single": [
|
| 53 |
+
{
|
| 54 |
+
"Sequence": {
|
| 55 |
+
"id": "A",
|
| 56 |
+
"type_id": 0
|
| 57 |
+
}
|
| 58 |
+
}
|
| 59 |
+
],
|
| 60 |
+
"pair": [
|
| 61 |
+
{
|
| 62 |
+
"Sequence": {
|
| 63 |
+
"id": "A",
|
| 64 |
+
"type_id": 0
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"Sequence": {
|
| 69 |
+
"id": "B",
|
| 70 |
+
"type_id": 1
|
| 71 |
+
}
|
| 72 |
+
}
|
| 73 |
+
],
|
| 74 |
+
"special_tokens": {}
|
| 75 |
+
},
|
| 76 |
"decoder": {
|
| 77 |
"type": "Sequence",
|
| 78 |
"decoders": [
|
tokenizer_config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
|
|
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
"pad_token": "<pad>",
|
| 9 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
+
"model_file": "tmp_factory/tokenizer_tr/spm.model",
|
| 8 |
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
"pad_token": "<pad>",
|
| 10 |
"tokenizer_class": "LlamaTokenizer",
|