init
Browse files- config.json +19 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +13 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForPretraining"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"hidden_act": "gelu",
|
| 7 |
+
"hidden_dropout_prob": 0.1,
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 3072,
|
| 11 |
+
"layer_norm_eps": 1e-12,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "bert",
|
| 14 |
+
"num_attention_heads": 12,
|
| 15 |
+
"num_hidden_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"type_vocab_size": 2,
|
| 18 |
+
"vocab_size": 35000
|
| 19 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:529500c36c4ce5a1f90715589f46702c350b334b8ce3cd74e7ae4e9b103e804b
|
| 3 |
+
size 284118515
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "[UNK]",
|
| 3 |
+
"sep_token": "[SEP]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"mask_token": "[MASK]"
|
| 7 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_lower_case": false,
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"never_split": null,
|
| 5 |
+
"unk_token": "[UNK]",
|
| 6 |
+
"sep_token": "[SEP]",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"cls_token": "[CLS]",
|
| 9 |
+
"mask_token": "[MASK]",
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"model_max_length": 512
|
| 13 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|