ayoubkirouane
commited on
Commit
•
bebd7c1
1
Parent(s):
664660a
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- ayoubkirouane/captcha
|
4 |
+
- project-sloth/captcha-images
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: transformers
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
---
|
10 |
+
|
11 |
+
## Base Model :
|
12 |
+
- vikhyatk/moondream2
|
13 |
+
|
14 |
+
## Dataset :
|
15 |
+
- project-sloth/captcha-images
|
16 |
+
|
17 |
+
|
18 |
+
|
19 |
+
# Load model :
|
20 |
+
|
21 |
+
|
22 |
+
```python
|
23 |
+
|
24 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
25 |
+
from PIL import Image
|
26 |
+
|
27 |
+
model_id = "ayoubkirouane/moondream2-image-captcha"
|
28 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
|
29 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id , trust_remote_code=True)
|
30 |
+
|
31 |
+
image = Image.open('/content/test.png')
|
32 |
+
enc_image = model.encode_image(image)
|
33 |
+
print(model.answer_question(enc_image, "What does the text say?", tokenizer))
|
34 |
+
|
35 |
+
|
36 |
+
```
|