Training in progress, step 10000
Browse files- config.json +23 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "relu",
|
3 |
+
"architectures": [
|
4 |
+
"DistilBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.005,
|
7 |
+
"dim": 512,
|
8 |
+
"dropout": 0.005,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"hidden_dim": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "hybridbert",
|
14 |
+
"n_heads": 8,
|
15 |
+
"n_layers": 10,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.005,
|
18 |
+
"seq_classif_dropout": 0.005,
|
19 |
+
"sinusoidal_pos_embds": true,
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.33.2",
|
22 |
+
"vocab_size": 30522
|
23 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f73670ad50ab7abd268dabe465389bdfde7c3a0c6a3e7ea9c00caf1a7e9d044
|
3 |
+
size 174325189
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87d68d64f41cc80578cc03a8299ae1837fa5961f3bdbce28def21a3c919c995f
|
3 |
+
size 5115
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|