Upload folder using huggingface_hub

README.md

@@ -1,12 +1,13 @@
 ---
-title: MedicalChatbot Phi3.5 Mini
-emoji: 👀
-colorFrom: green
-colorTo: blue
+title: MedicalChatbot-Phi3.5-mini
+app_file: app.py
 sdk: gradio
 sdk_version: 5.15.0
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+title: RomanEng2Nep-v2
+emoji: ⚕️
+colorFrom: purple
+colorTo: red
+app_file: app.py
+sdk: gradio
+sdk_version: 5.15.0

app.py

@@ -0,0 +1,63 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import gradio as gr
+import spaces
+
+torch.cuda.empty_cache()
+device = "cuda" if torch.cuda.is_available() else "cpu"
+print(f"Using device: {device}")
+
+model_name = "syubraj/MedicalChat-Phi-3.5-mini-instruct"
+try:
+    model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    print("Model and Tokenizer loaded successfully.")
+except Exception as e:
+    raise ValueError(f"Error loading Model and Tokenizer: {e}")
+
+@spaces.GPU
+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.
+    :return: Generated assistant response.
+    """
+    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.")
+    
+    prompt = f"<|system|> {system_message} <|end|> <|user|> {user_query} <|end|> <|assistant|>"
+    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()
+    except Exception as e:
+        return f"Error generating response: {e}"
+
+# Gradio Interface
+def chat_interface(user_query, system_message=None):
+    response = generate_response(user_query, system_message)
+    return response
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Medical Chatbot")
+    gr.Markdown("Ask your medical questions, and the AI will provide professional responses.")
+    
+    with gr.Row():
+        user_query = gr.Textbox(label="Your Query", placeholder="Enter your question here...", lines=3)
+        system_message = gr.Textbox(label="System Message (Optional)", placeholder="Custom system instruction...", lines=3)
+    
+    submit_button = gr.Button("Submit")
+    output = gr.Textbox(label="Assistant Response", lines=5)
+    
+    submit_button.click(chat_interface, inputs=[user_query, system_message], outputs=output)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,7 @@
+transformers==4.48.2
+peft==0.14.0
+bitsandbytes==0.45.1
+gradio==5.15.0
+accelerate==1.3.0
+torch==2.4.0
+spaces==0.32.0