Upload 6 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+images/image1.jpg filter=lfs diff=lfs merge=lfs -text
+images/image2.jpg filter=lfs diff=lfs merge=lfs -text
+images/image3.jpg filter=lfs diff=lfs merge=lfs -text
+images/image4.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,55 @@
+import ast
+import torch
+import gradio as gr
+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"
+
+
+processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-256M-Instruct")
+model = AutoModelForVision2Seq.from_pretrained(
+    "Hirai-Labs/FT-SmolVLM-500M-Instruct-ALPR",
+    torch_dtype=torch.bfloat16,
+    _attn_implementation="eager" if DEVICE == "cuda" else "eager",
+).to(DEVICE)
+
+# Create input messages
+messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "You are an AI assistant whose job is to inspect an image and provide the desired information from the image. If the desired field is not clear or not well detected, return None for this field. Do not try to guess."},
+                {"type": "image"},
+                {"type": "text", "text": 'The output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}\nthe object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{"properties": {"type": {"title": "Type", "description": "Return the type of the vehicle", "examples": ["Car", "Truck", "Motorcycle", "Bus"], "type": "string"}, "license_plate": {"title": "License Plate", "description": "Return the license plate number of the vehicle", "type": "string"}, "make": {"title": "Make", "description": "Return the Make of the vehicle", "examples": ["Toyota", "Honda", "Ford", "Suzuki"], "type": "string"}, "model": {"title": "Model", "description": "Return the model of the vehicle", "examples": ["Corolla", "Civic", "F-150"], "type": "string"}, "color": {"title": "Color", "description": "Return the color of the vehicle", "examples": ["Red", "Blue", "Black", "White"], "type": "string"}}, "required": ["type", "license_plate", "make", "model", "color"]}\n```'}
+            ]
+        }
+    ]
+
+def predictor(image):
+    image = load_image(image=image)
+    prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+    inputs = processor(text=prompt, images=[image], return_tensors="pt")
+    inputs = inputs.to(DEVICE)
+
+    generated_ids = model.generate(**inputs, max_new_tokens=500)
+    generated_texts = processor.batch_decode(
+        generated_ids,
+        skip_special_tokens=True,
+    )
+    output = generated_texts[0]
+
+
+    assistant_part = output.split("Assistant: ")[1]        
+    dict_data = ast.literal_eval(assistant_part)
+    return dict_data
+
+iface = gr.Interface(
+    fn=predictor,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    examples=["images/image1.jpg", "images/image2.jpg", "images/image3.jpg", "images/image4.jpg"]
+)
+
+iface.launch(server_name="0.0.0.0", server_port=8080)

requirements.txt

@@ -0,0 +1,62 @@
+accelerate==1.4.0
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.8.0
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+fastapi==0.115.8
+ffmpy==0.5.0
+filelock==3.17.0
+fsspec==2025.2.0
+gradio==5.17.0
+gradio_client==1.7.1
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+huggingface-hub==0.29.1
+idna==3.10
+Jinja2==3.1.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.4.2
+numpy==2.2.3
+orjson==3.10.15
+packaging==24.2
+pandas==2.2.3
+peft==0.14.0
+pillow==11.1.0
+psutil==7.0.0
+pydantic==2.10.6
+pydantic_core==2.27.2
+pydub==0.25.1
+Pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+ruff==0.9.7
+safehttpx==0.1.6
+safetensors==0.5.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.45.3
+sympy==1.13.1
+tokenizers==0.21.0
+tomlkit==0.13.2
+torch==2.6.0+cpu
+tqdm==4.67.1
+transformers==4.49.0
+typer==0.15.1
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+uvicorn==0.34.0
+websockets==14.2