Upload folder using huggingface_hub
Browse files- config.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +35 -5
- tokenizer_config.json +4 -0
config.json
CHANGED
|
@@ -39,6 +39,7 @@
|
|
| 39 |
"num_hidden_layers": 12,
|
| 40 |
"pad_token_id": 0,
|
| 41 |
"position_embedding_type": "absolute",
|
|
|
|
| 42 |
"transformers_version": "4.52.4",
|
| 43 |
"type_vocab_size": 2,
|
| 44 |
"use_cache": true,
|
|
|
|
| 39 |
"num_hidden_layers": 12,
|
| 40 |
"pad_token_id": 0,
|
| 41 |
"position_embedding_type": "absolute",
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
"transformers_version": "4.52.4",
|
| 44 |
"type_vocab_size": 2,
|
| 45 |
"use_cache": true,
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50b62e62ca804df5c5fc35492efc36600043093e1088f6e7e31f307046116161
|
| 3 |
+
size 18680
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"cls_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 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 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
}
|
tokenizer_config.json
CHANGED
|
@@ -46,11 +46,15 @@
|
|
| 46 |
"do_lower_case": false,
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
"mask_token": "[MASK]",
|
|
|
|
| 49 |
"model_max_length": 512,
|
| 50 |
"pad_token": "[PAD]",
|
| 51 |
"sep_token": "[SEP]",
|
|
|
|
| 52 |
"strip_accents": null,
|
| 53 |
"tokenize_chinese_chars": true,
|
| 54 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 55 |
"unk_token": "[UNK]"
|
| 56 |
}
|
|
|
|
| 46 |
"do_lower_case": false,
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
"model_max_length": 512,
|
| 51 |
"pad_token": "[PAD]",
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
+
"stride": 0,
|
| 54 |
"strip_accents": null,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"truncation_side": "right",
|
| 58 |
+
"truncation_strategy": "longest_first",
|
| 59 |
"unk_token": "[UNK]"
|
| 60 |
}
|