cagri coltekin
commited on
Commit
•
2982026
1
Parent(s):
7236ba8
First version.
Browse files- README.md +14 -0
- config.json +42 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: tr
|
3 |
+
datasets:
|
4 |
+
- tremo
|
5 |
+
---
|
6 |
+
|
7 |
+
# BERTurk fine-tuned on emotion classification
|
8 |
+
|
9 |
+
This model is [BERTurk cased](https://huggingface.co/dbmdz/bert-base-turkish-cased)
|
10 |
+
model finetuned on the [TREMO](http://demir.cs.deu.edu.tr/TREMO) data
|
11 |
+
set for Turkis emotion classification.
|
12 |
+
|
13 |
+
The macro-average F1 score of the model is approximately 94% on a
|
14 |
+
randomly set aside development set of 2k instances.
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "final-model",
|
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": "Anger",
|
13 |
+
"1": "Disgust",
|
14 |
+
"2": "Fear",
|
15 |
+
"3": "Happy",
|
16 |
+
"4": "Sadness",
|
17 |
+
"5": "Surprise"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"Anger": 0,
|
23 |
+
"Disgust": 1,
|
24 |
+
"Fear": 2,
|
25 |
+
"Happy": 3,
|
26 |
+
"Sadness": 4,
|
27 |
+
"Surprise": 5
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-12,
|
30 |
+
"max_position_embeddings": 512,
|
31 |
+
"model_type": "bert",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"pad_token_id": 0,
|
35 |
+
"position_embedding_type": "absolute",
|
36 |
+
"problem_type": "single_label_classification",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.25.1",
|
39 |
+
"type_vocab_size": 2,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 32000
|
42 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e802d289a89af3c5d435140d8be9b28b4cf976780fbad40f69322a5a13810b6
|
3 |
+
size 442560629
|
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 sha256:9d6af0854f607b24209d03643321da944af4f90e442a718199caa0b5019552f9
|
3 |
+
size 442775848
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"model_max_length": 512,
|
8 |
+
"name_or_path": "dbmdz/bert-base-turkish-cased",
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53fdc1a900c91b59fb1102ee118597490b51684f1880b15677da71664be9680f
|
3 |
+
size 3387
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|