Update app.py

app.py

@@ -1,63 +1,65 @@
 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 AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the tokenizer and quantized model from Hugging Face
+model_name = "llSourcell/medllama2_7b"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Load model with quantization
+model = AutoModelForCausalLM.from_pretrained(model_name, 
+                                             load_in_4bit=True, 
+                                             device_map="auto",
+                                             quantization_config={
+                                                 'bits': 4,  # Quantize to 4-bit
+                                                 'group_size': 128
+                                             })
+
+def format_history(msg: str, history: list[list[str, str]], system_prompt: str):
+    chat_history = system_prompt
+    for query, response in history:
+        chat_history += f"\nUser: {query}\nAssistant: {response}"
+    chat_history += f"\nUser: {msg}\nAssistant:"
+    return chat_history
+
+def generate_response(msg: str, history: list[list[str, str]], system_prompt: str):
+    chat_history = format_history(msg, history, system_prompt)
+    
+    # Tokenize the input prompt
+    inputs = tokenizer(chat_history, return_tensors="pt").to("cuda")
+    
+    # Generate a response using the model
+    outputs = model.generate(inputs["input_ids"], max_length=500, pad_token_id=tokenizer.eos_token_id)
+
+    # Decode the response back to a string
+    response = tokenizer.decode(outputs[:, inputs["input_ids"].shape[-1]:][0], skip_special_tokens=True)
+    
+    # Yield the generated response
+    yield response
+
+# Define the Gradio ChatInterface
+chatbot = gr.ChatInterface(
+                generate_response,
+                chatbot=gr.Chatbot(
+                        height="64vh"
+                    ),
+                additional_inputs=[
+                    gr.Textbox(
+                        "Behave as if you are a medical doctor providing answers for patients' clinical questions.",
+                        label="System Prompt"
+                    )
+                ],
+                title="Medical QA Chat",
+                description="Feel free to ask any question to Medllama2 Chatbot.",
+                theme="soft",
+                submit_btn="Send",
+                retry_btn="Regenerate Response",
+                undo_btn="Delete Previous",
+                clear_btn="Clear Chat"
 )
 
+# Following line is important to queue the messages
+chatbot.queue()
 
-if __name__ == "__main__":
-    demo.launch()
+# Enable share = True if you want to create a public link for people to use your application
+chatbot.launch()