Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Indonesia Recipe Ingredients Generator Model
|
2 |
|
3 |
-
|
|
|
|
|
|
|
|
|
4 |
|
5 |
This is a fine-tuned model to generate the Indonesian food ingredients. One of my personal project that I did in my free time.
|
6 |
|
@@ -8,18 +20,18 @@ Basically, you give the name of the food and it will produce the ingredients of
|
|
8 |
|
9 |
## Model
|
10 |
|
11 |
-
Data: [Indonesian Recipe Data on Kaggle](https://www.kaggle.com/datasets/canggih/indonesian-food-recipes)
|
12 |
Pre-trained Model: [IndoBART-v2](https://huggingface.co/indobenchmark/indobart-v2)
|
13 |
|
14 |
## How to use
|
15 |
|
16 |
-
We will specify the
|
17 |
|
18 |
### Tokenizer
|
19 |
|
20 |
Since we use `indobart-v2`, we need to use their tokenizer.
|
21 |
|
22 |
-
First, install the tokenizer
|
23 |
|
24 |
After that, you can load the tokenizer:
|
25 |
|
@@ -52,6 +64,4 @@ nasi goreng ayam
|
|
52 |
|
53 |
~To be continued
|
54 |
|
55 |
-
|
56 |
-
license: mit
|
57 |
-
---
|
|
|
1 |
+
---
|
2 |
+
language: id
|
3 |
+
tags:
|
4 |
+
- bart
|
5 |
+
- id
|
6 |
+
license: mit
|
7 |
+
---
|
8 |
+
|
9 |
# Indonesia Recipe Ingredients Generator Model
|
10 |
|
11 |
+
**WARNING: inference on Huggingface might not run since the tokenizer is not the default one. Currently, I want to build a spaces to run the inference.
|
12 |
+
Please wait for it**
|
13 |
+
|
14 |
+
|
15 |
+
π **Have fun on generating ingredients** π
|
16 |
|
17 |
This is a fine-tuned model to generate the Indonesian food ingredients. One of my personal project that I did in my free time.
|
18 |
|
|
|
20 |
|
21 |
## Model
|
22 |
|
23 |
+
Data: [Indonesian Recipe Data on Kaggle](https://www.kaggle.com/datasets/canggih/indonesian-food-recipes)
|
24 |
Pre-trained Model: [IndoBART-v2](https://huggingface.co/indobenchmark/indobart-v2)
|
25 |
|
26 |
## How to use
|
27 |
|
28 |
+
We will specify the usage of the tokenizer and the model.
|
29 |
|
30 |
### Tokenizer
|
31 |
|
32 |
Since we use `indobart-v2`, we need to use their tokenizer.
|
33 |
|
34 |
+
First, install the tokenizer by doing `pip install indobenchmark-toolkit`.
|
35 |
|
36 |
After that, you can load the tokenizer:
|
37 |
|
|
|
64 |
|
65 |
~To be continued
|
66 |
|
67 |
+
|
|
|
|