Create app.py

app.py

@@ -0,0 +1,47 @@
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForVision2Seq
+import gradio as gr
+import os
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+token = os.environ.get("HF_TOKEN")
+
+processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct", token=token)
+model = AutoModelForVision2Seq.from_pretrained(
+    "HuggingFaceTB/SmolVLM-Instruct",
+    torch_dtype=torch.bfloat16 if DEVICE == "cuda" else torch.float32,
+    _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
+    token=token
+).to(DEVICE)
+
+def describe_image(image):
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "image"},
+                {"type": "text", "text": "Describe this image in detail."}
+            ]
+        },
+    ]
+
+    prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+    inputs = processor(text=prompt, images=[image], return_tensors="pt").to(DEVICE)
+
+    with torch.no_grad():
+        generated_ids = model.generate(**inputs, max_new_tokens=500)
+
+    result = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return result
+
+demo = gr.Interface(
+    fn=describe_image,
+    inputs=gr.Image(type="pil", label="Upload an Image"),
+    outputs="text",
+    title="VISIONSAGE",
+    description="Upload an image and get a detailed description."
+)
+
+demo.launch()