Update app.py

app.py

@@ -1,64 +1,39 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+from transformers import AutoProcessor, AutoModelForImageTextToText
+import torch
+from PIL import Image
+
+# Load the processor and model
+processor = AutoProcessor.from_pretrained("guneetsk99/finance_qwen_VL_7B")
+model = AutoModelForImageTextToText.from_pretrained("guneetsk99/finance_qwen_VL_7B")
+
+def predict(input_img, text_prompt):
+    # Preprocess the image and text prompt
+    inputs = processor(images=input_img, text=text_prompt, return_tensors="pt").to(model.device)
+    
+    # Generate predictions using the model
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=50)
+    
+    # Decode the generated text
+    generated_text = processor.decode(outputs[0], skip_special_tokens=True)
+    
+    return input_img, generated_text
+
+# Create the Gradio interface
+gradio_app = gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Image(label="Upload Image", source="upload", type="pil"),
+        gr.Textbox(label="Text Prompt", placeholder="Enter a text prompt, e.g., 'Describe this image.'"),
+    ],
+    outputs=[
+        gr.Image(label="Uploaded Image"),
+        gr.Textbox(label="Generated Response"),
     ],
+    title="Finance Image-to-Text Model",
+    description="Upload a financial document image and provide a text prompt for the model to process the image and generate a text response.",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    gradio_app.launch()