Upload folder using huggingface_hub

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

README.md

@@ -7,3 +7,28 @@ app_file: app.py
 sdk: gradio
 sdk_version: 5.15.0
 ---
+# MedicalChatbot-Phi3.5
+
+## Getting Started
+1. Create virtual environment
+```python
+python -m venv venv
+```
+
+2. Activate virtual environment
+```python
+source venv/bin/activate
+```
+
+3. Install Required packages
+```python
+pip install -r requirements.txt
+```
+
+## Run Gradio App
+```python
+python app.py
+```
+
+## Sample Output
+![image](https://github.com/user-attachments/assets/705a89d2-02f3-4398-8f99-5d4aefb5f745)

app.py

@@ -1,4 +1,4 @@
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import torch
 import gradio as gr
 import spaces
@@ -15,10 +15,12 @@ try:
 except Exception as e:
     raise ValueError(f"Error loading Model and Tokenizer: {e}")
 
-@spaces.GPU
+@torch.inference_mode()
+@spaces.GPU(duration=120)
 def generate_response(user_query: str, system_message: str = None, max_length: int = 1024) -> str:
     """
     Generates a response based on the given user query.
+
     :param user_query: The user's input message.
     :param system_message: Custom system instruction (optional, defaults to medical assistant).
     :param max_length: Max tokens to generate.
@@ -26,23 +28,36 @@ def generate_response(user_query: str, system_message: str = None, max_length: i
     """
     if not user_query.strip():
         return "Error: User query cannot be empty."
-    
+
     if system_message is None:
         system_message = ("You are a trusted AI-powered medical assistant. "
                           "Analyze patient queries carefully and provide accurate, professional, and empathetic responses. "
                           "Prioritize patient safety, adhere to medical best practices, and recommend consulting a healthcare provider when necessary.")
+
+    messages = [
+        {"role": "system", "content": system_message},
+        {'role': "user", "content": user_query}
+    ]
+
+    pipe = pipeline("text-generation",
+                    model=model, 
+                    tokenizer=tokenizer)
     
-    prompt = f"<|system|> {system_message} <|end|> <|user|> {user_query} <|end|> <|assistant|>"
+    generation_args = {
+        "max_new_tokens": max_length,
+        "return_full_text": False,
+        "temperature": 0.0,
+        "do_sample": False,
+}
     try:
-        inputs = tokenizer(prompt, return_tensors="pt").to(device)
-        outputs = model.generate(**inputs, max_length=max_length)
-        # Decode response
-        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return response.split("<|assistant|>")[-1].strip().split("<|end|>")[0].strip()
+        output = pipe(messages, **generation_args)
+        return(output[0]['generated_text'])
     except Exception as e:
         return f"Error generating response: {e}"
 
 # Gradio Interface
+@torch.inference_mode()
+@spaces.GPU(duration=120)
 def chat_interface(user_query, system_message=None):
     response = generate_response(user_query, system_message)
     return response
@@ -60,4 +75,6 @@ with gr.Blocks() as demo:
     
     submit_button.click(chat_interface, inputs=[user_query, system_message], outputs=output)
 
-demo.launch()
+demo.launch(share=True)
+
+