Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import AutoProcessor, Gemma3nForConditionalGeneration
|
2 |
+
from PIL import Image
|
3 |
+
import requests
|
4 |
+
import torch
|
5 |
+
|
6 |
+
model_id = "google/gemma-3n-e4b-it"
|
7 |
+
|
8 |
+
model = Gemma3nForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,).eval()
|
9 |
+
|
10 |
+
processor = AutoProcessor.from_pretrained(model_id)
|
11 |
+
|
12 |
+
messages = [
|
13 |
+
{
|
14 |
+
"role": "system",
|
15 |
+
"content": [{"type": "text", "text": "You are a helpful assistant."}]
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"role": "user",
|
19 |
+
"content": [
|
20 |
+
{"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
|
21 |
+
{"type": "text", "text": "Describe this image in detail."}
|
22 |
+
]
|
23 |
+
}
|
24 |
+
]
|
25 |
+
|
26 |
+
inputs = processor.apply_chat_template(
|
27 |
+
messages,
|
28 |
+
add_generation_prompt=True,
|
29 |
+
tokenize=True,
|
30 |
+
return_dict=True,
|
31 |
+
return_tensors="pt",
|
32 |
+
).to(model.device)
|
33 |
+
|
34 |
+
input_len = inputs["input_ids"].shape[-1]
|
35 |
+
|
36 |
+
with torch.inference_mode():
|
37 |
+
generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
|
38 |
+
generation = generation[0][input_len:]
|
39 |
+
|
40 |
+
decoded = processor.decode(generation, skip_special_tokens=True)
|
41 |
+
print(decoded)
|
42 |
+
|
43 |
+
# **Overall Impression:** The image is a close-up shot of a vibrant garden scene,
|
44 |
+
# focusing on a cluster of pink cosmos flowers and a busy bumblebee.
|
45 |
+
# It has a slightly soft, natural feel, likely captured in daylight.
|