digo-prayudha
commited on
Commit
•
183c3be
1
Parent(s):
320a142
Update README.md
Browse files
README.md
CHANGED
@@ -4,10 +4,13 @@ base_model: indolem/indobert-base-uncased
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
- indoqa
|
8 |
model-index:
|
9 |
- name: IndoQA
|
10 |
results: []
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,23 +18,23 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# IndoQA
|
17 |
|
18 |
-
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 1.4807
|
21 |
|
22 |
-
|
23 |
|
24 |
-
|
|
|
25 |
|
26 |
-
|
|
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
## Training procedure
|
35 |
|
36 |
### Training hyperparameters
|
37 |
|
@@ -58,4 +61,4 @@ The following hyperparameters were used during training:
|
|
58 |
- Transformers 4.35.2
|
59 |
- Pytorch 2.1.0+cu121
|
60 |
- Datasets 2.15.0
|
61 |
-
- Tokenizers 0.15.0
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- jakartaresearch/indoqa
|
8 |
model-index:
|
9 |
- name: IndoQA
|
10 |
results: []
|
11 |
+
language:
|
12 |
+
- id
|
13 |
+
pipeline_tag: question-answering
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
18 |
|
19 |
# IndoQA
|
20 |
|
21 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on [jakartaresearch/indoqa](https://huggingface.co/datasets/jakartaresearch/indoqa).
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 1.4807
|
24 |
|
25 |
+
### How to use this model in Transformers Library
|
26 |
|
27 |
+
```python
|
28 |
+
from transformers import pipeline
|
29 |
|
30 |
+
question = "Berapa jumlah pulau yang ada di indonesia?"
|
31 |
+
context = "Indonesia adalah negara kepulauan, Dengan jumlah pulau sekitar 17 ribu"
|
32 |
|
33 |
+
from transformers import pipeline
|
34 |
|
35 |
+
question_answerer = pipeline("question-answering", model="digo-prayudha/IndoQA")
|
36 |
+
question_answerer(question=question, context=context)
|
37 |
+
```
|
|
|
|
|
38 |
|
39 |
### Training hyperparameters
|
40 |
|
|
|
61 |
- Transformers 4.35.2
|
62 |
- Pytorch 2.1.0+cu121
|
63 |
- Datasets 2.15.0
|
64 |
+
- Tokenizers 0.15.0
|