raygx commited on
Commit
c1d7f5c
1 Parent(s): f1aa762

Upload TFBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +49 -0
  2. config.json +35 -0
  3. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: raygx/BertClassifier4NepaliNews
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: BERT-NepSA-domainAdapt
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # BERT-NepSA-domainAdapt
15
+
16
+ This model is a fine-tuned version of [raygx/BertClassifier4NepaliNews](https://huggingface.co/raygx/BertClassifier4NepaliNews) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.05}
38
+ - training_precision: float32
39
+
40
+ ### Training results
41
+
42
+
43
+
44
+ ### Framework versions
45
+
46
+ - Transformers 4.32.0
47
+ - TensorFlow 2.12.0
48
+ - Datasets 2.14.4
49
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "raygx/BertClassifier4NepaliNews",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "NEUTRAL",
13
+ "1": "POSITIVE",
14
+ "2": "NEGATIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NEGATIVE": 2,
20
+ "NEUTRAL": 0,
21
+ "POSITIVE": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.32.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080ab3752fe54af6185c2d5157a329f9701486b09fd28d1d2f77b78b1c946959
3
+ size 438226204