Uploading the fine tuned distillbert model on mtsamples clinical notes
Browse filesThis a fine tuned model of distillbert for my project Wellnation - so named "dwellbert".
- config.json +37 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1,
|
22 |
+
"LABEL_2": 2,
|
23 |
+
"LABEL_3": 3,
|
24 |
+
"LABEL_4": 4
|
25 |
+
},
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "distilbert",
|
28 |
+
"n_heads": 12,
|
29 |
+
"n_layers": 6,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"qa_dropout": 0.1,
|
32 |
+
"seq_classif_dropout": 0.2,
|
33 |
+
"sinusoidal_pos_embds": false,
|
34 |
+
"tie_weights_": true,
|
35 |
+
"transformers_version": "4.29.1",
|
36 |
+
"vocab_size": 30522
|
37 |
+
}
|
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 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da574063e92fe095da263c692b1b4c6f9ba283fef8478fba225390b1a6a0dc4b
|
3 |
+
size 267964360
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "DistilBertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|