minnehwg commited on
Commit
fc221a2
·
verified ·
1 Parent(s): 8eb939d

Upload TFDistilBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +49 -0
  2. config.json +44 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert-base-multilingual-cased
5
+ tags:
6
+ - generated_from_keras_callback
7
+ model-index:
8
+ - name: vnexpress-title-classification
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
13
+ probably proofread and complete it, then remove this comment. -->
14
+
15
+ # vnexpress-title-classification
16
+
17
+ This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - optimizer: None
39
+ - training_precision: float32
40
+
41
+ ### Training results
42
+
43
+
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.47.1
48
+ - TensorFlow 2.18.0
49
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
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
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "label2id": {
23
+ "LABEL_0": 0,
24
+ "LABEL_1": 1,
25
+ "LABEL_2": 2,
26
+ "LABEL_3": 3,
27
+ "LABEL_4": 4,
28
+ "LABEL_5": 5,
29
+ "LABEL_6": 6,
30
+ "LABEL_7": 7
31
+ },
32
+ "max_position_embeddings": 512,
33
+ "model_type": "distilbert",
34
+ "n_heads": 12,
35
+ "n_layers": 6,
36
+ "output_past": true,
37
+ "pad_token_id": 0,
38
+ "qa_dropout": 0.1,
39
+ "seq_classif_dropout": 0.2,
40
+ "sinusoidal_pos_embds": false,
41
+ "tie_weights_": true,
42
+ "transformers_version": "4.47.1",
43
+ "vocab_size": 119547
44
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52048fbd6f5ccb02e4e737322d0d4a3ef4e01004390471231a76e51ae3216755
3
+ size 541455040