Commit
·
fe86b68
1
Parent(s):
c672dbe
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,7 @@ It achieves the following results on the evaluation set:
|
|
| 36 |
- F1: 95.084
|
| 37 |
- Gen Len: 2.4976
|
| 38 |
|
| 39 |
-
```
|
| 40 |
precision recall f1-score support
|
| 41 |
|
| 42 |
0 0.97 0.88 0.92 12500
|
|
@@ -56,12 +56,12 @@ This model was trained on the imdb train dataset with 25,000 data and then teste
|
|
| 56 |
|
| 57 |
## Usage
|
| 58 |
|
| 59 |
-
|
| 60 |
```python
|
| 61 |
!pip install transformers==4.28.1 datasets
|
| 62 |
```
|
| 63 |
|
| 64 |
-
|
| 65 |
```python
|
| 66 |
from datasets import load_dataset
|
| 67 |
|
|
@@ -71,7 +71,7 @@ dataset_id = "imdb"
|
|
| 71 |
dataset = load_dataset(dataset_id)
|
| 72 |
```
|
| 73 |
|
| 74 |
-
|
| 75 |
```python
|
| 76 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 77 |
tokenizer = AutoTokenizer.from_pretrained("mohammadtaghizadeh/flan-t5-base-imdb-text-classification")
|
|
@@ -79,7 +79,7 @@ model = AutoModelForSeq2SeqLM.from_pretrained("mohammadtaghizadeh/flan-t5-base-i
|
|
| 79 |
model.to('cuda')
|
| 80 |
```
|
| 81 |
|
| 82 |
-
|
| 83 |
```python
|
| 84 |
from tqdm.auto import tqdm
|
| 85 |
|
|
@@ -98,7 +98,7 @@ for i in range(samples_number):
|
|
| 98 |
progress_bar.update(1)
|
| 99 |
```
|
| 100 |
|
| 101 |
-
|
| 102 |
```python
|
| 103 |
from sklearn.metrics import classification_report
|
| 104 |
|
|
@@ -109,7 +109,7 @@ report = classification_report(str_labels_list, predictions_list)
|
|
| 109 |
print(report)
|
| 110 |
```
|
| 111 |
|
| 112 |
-
|
| 113 |
```cmd
|
| 114 |
precision recall f1-score support
|
| 115 |
|
|
|
|
| 36 |
- F1: 95.084
|
| 37 |
- Gen Len: 2.4976
|
| 38 |
|
| 39 |
+
```cmd
|
| 40 |
precision recall f1-score support
|
| 41 |
|
| 42 |
0 0.97 0.88 0.92 12500
|
|
|
|
| 56 |
|
| 57 |
## Usage
|
| 58 |
|
| 59 |
+
1. Install dependencies
|
| 60 |
```python
|
| 61 |
!pip install transformers==4.28.1 datasets
|
| 62 |
```
|
| 63 |
|
| 64 |
+
2. Load IMDB Corpus
|
| 65 |
```python
|
| 66 |
from datasets import load_dataset
|
| 67 |
|
|
|
|
| 71 |
dataset = load_dataset(dataset_id)
|
| 72 |
```
|
| 73 |
|
| 74 |
+
3. Load fine tune flan t5 model
|
| 75 |
```python
|
| 76 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 77 |
tokenizer = AutoTokenizer.from_pretrained("mohammadtaghizadeh/flan-t5-base-imdb-text-classification")
|
|
|
|
| 79 |
model.to('cuda')
|
| 80 |
```
|
| 81 |
|
| 82 |
+
4. Test the model
|
| 83 |
```python
|
| 84 |
from tqdm.auto import tqdm
|
| 85 |
|
|
|
|
| 98 |
progress_bar.update(1)
|
| 99 |
```
|
| 100 |
|
| 101 |
+
5. Classification report
|
| 102 |
```python
|
| 103 |
from sklearn.metrics import classification_report
|
| 104 |
|
|
|
|
| 109 |
print(report)
|
| 110 |
```
|
| 111 |
|
| 112 |
+
Output
|
| 113 |
```cmd
|
| 114 |
precision recall f1-score support
|
| 115 |
|