Update app.py

app.py

@@ -1,64 +1,90 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoProcessor, AutoModelForCausalLM
+import spaces
 
-"""
-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")
 
+from PIL import Image 
 
-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]})
+import subprocess
+# subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
-    messages.append({"role": "user", "content": message})
+model = AutoModelForCausalLM.from_pretrained('HuggingFaceM4/Florence-2-DocVQA', trust_remote_code=True).to("cuda").eval()
 
-    response = ""
+processor = AutoProcessor.from_pretrained('HuggingFaceM4/Florence-2-DocVQA', trust_remote_code=True)
 
-    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
+TITLE = "# [Descripta Demo](https://huggingface.co/HuggingFaceM4/Florence-2-DocVQA)"
+DESCRIPTION = "The demo for Florence-2 fine-tuned on DocVQA dataset. You can find the notebook [here](https://colab.research.google.com/drive/1hKDrJ5AH_o7I95PtZ9__VlCTNAo1Gjpf?usp=sharing). Read more about Florence-2 fine-tuning [here](finetune-florence2)."
 
 
+colormap = ['blue','orange','green','purple','brown','pink','gray','olive','cyan','red',
+            'lime','indigo','violet','aqua','magenta','coral','gold','tan','skyblue']
+
+@spaces.GPU
+def run_example(task_prompt, image, text_input=None):
+    if text_input is None:
+        prompt = task_prompt
+    else:
+        prompt = task_prompt + text_input
+    inputs = processor(text=prompt, images=image, return_tensors="pt").to("cuda")
+    generated_ids = model.generate(
+        input_ids=inputs["input_ids"],
+        pixel_values=inputs["pixel_values"],
+        max_new_tokens=1024,
+        early_stopping=False,
+        do_sample=False,
+        num_beams=3,
+    )
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
+    parsed_answer = processor.post_process_generation(
+        generated_text,
+        task=task_prompt,
+        image_size=(image.width, image.height)
+    )
+    return parsed_answer
+
+def process_image(image, text_input=None):
+    image = Image.fromarray(image)  # Convert NumPy array to PIL Image
+    task_prompt = '<DocVQA>'
+    results = run_example(task_prompt, image, text_input)[task_prompt].replace("<pad>", "")
+    return results
+
+
+css = """
+  #output {
+    height: 500px; 
+    overflow: auto; 
+    border: 1px solid #ccc; 
+  }
 """
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown(TITLE)
+    gr.Markdown(DESCRIPTION)
+    with gr.Tab(label="Florence-2 Image Captioning"):
+        with gr.Row():
+            with gr.Column():
+                input_img = gr.Image(label="Input Picture")
+                text_input = gr.Textbox(label="Text Input (optional)")
+                submit_btn = gr.Button(value="Submit")
+            with gr.Column():
+                output_text = gr.Textbox(label="Output Text")
+
+        gr.Examples(
+            examples=[
+                ["hunt.jpg", 'What is this image?'],
+                ["idefics2_architecture.png", 'How many tokens per image does it use?'],
+                ["idefics2_architecture.png", "What type of encoder does the model use?"],
+                ["image.jpg", "What's the share of Industry Switchers Gained?"]
+            ],
+            inputs=[input_img, text_input],
+            outputs=[output_text],
+            fn=process_image,
+            cache_examples=True,
+            label='Try the examples below'
+        )
+
+        submit_btn.click(process_image, [input_img, text_input], [output_text])
+
+demo.launch(debug=True)