Mojtaba aka Omid Rohanian
commited on
Commit
•
44a5402
1
Parent(s):
23aaea6
First version of the bio-distilbert-cased model and tokenizer.
Browse files- config.json +31 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distil-biobert/models/distil-biobert-v2/final/model",
|
3 |
+
"activation": "gelu",
|
4 |
+
"adapters": {
|
5 |
+
"adapters": {},
|
6 |
+
"config_map": {},
|
7 |
+
"fusion_config_map": {},
|
8 |
+
"fusions": {}
|
9 |
+
},
|
10 |
+
"architectures": [
|
11 |
+
"DistilBertForMaskedLM"
|
12 |
+
],
|
13 |
+
"attention_dropout": 0.1,
|
14 |
+
"dim": 768,
|
15 |
+
"dropout": 0.1,
|
16 |
+
"hidden_dim": 3072,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.17.0",
|
30 |
+
"vocab_size": 28996
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cdc9c300de6fa374396b8b83ea46e625a65f5765857a1772db31f786adcd89a
|
3 |
+
size 263292335
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|