Upload main.py

main.py

@@ -0,0 +1,50 @@
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForVision2Seq
+from transformers.image_utils import load_image
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load images
+image = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
+
+# Initialize processor and model
+processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-500M-Instruct")
+model = AutoModelForVision2Seq.from_pretrained(
+    "HuggingFaceTB/SmolVLM-500M-Instruct",
+    torch_dtype=torch.bfloat16,
+    _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
+).to(DEVICE)
+
+# Create input messages
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image"},
+            {"type": "text", "text": "Can you describe this image?"}
+        ]
+    },
+]
+
+# Prepare inputs
+prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+inputs = processor(text=prompt, images=[image], return_tensors="pt")
+inputs = inputs.to(DEVICE)
+
+# Generate outputs
+generated_ids = model.generate(**inputs, max_new_tokens=500)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
+
+print(generated_texts[0])
+"""
+Assistant: The image depicts a cityscape featuring a prominent landmark, the Statue of Liberty, prominently positioned on Liberty Island. The statue is a green, humanoid figure with a crown atop its head and is situated on a small island surrounded by water. The statue is characterized by its large, detailed structure, with a statue of a woman holding a torch above her head and a tablet in her left hand. The statue is surrounded by a small, rocky island, which is partially visible in the foreground.
+In the background, the cityscape is dominated by numerous high-rise buildings, which are densely packed and vary in height. The buildings are primarily made of glass and steel, reflecting the sunlight and creating a bright, urban skyline. The skyline is filled with various architectural styles, including modern skyscrapers and older, more traditional buildings.
+The water surrounding the island is calm, with a few small boats visible, indicating that the area is likely a popular tourist destination. The water is a deep blue, suggesting that it is a large body of water, possibly a river or a large lake.
+In the foreground, there is a small strip of land with trees and grass, which adds a touch of natural beauty to the urban landscape. The trees are green, indicating that it is likely spring or summer.
+The image captures a moment of tranquility and reflection, as the statue and the cityscape come together to create a harmonious and picturesque scene. The statue's presence in the foreground draws attention to the city's grandeur, while the calm water and natural elements in the background provide a sense of peace and serenity.
+In summary, the image showcases the Statue of Liberty, a symbol of freedom and democracy, set against a backdrop of a bustling cityscape. The statue is a prominent and iconic representation of human achievement, while the cityscape is a testament to human ingenuity and progress. The image captures the beauty and complexity of urban life, with the statue serving as a symbol of hope and freedom, while the cityscape provides a glimpse into the modern world.
+"""