Update app.py

app.py

@@ -1,11 +1,14 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
 
-"""
-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")
+# Download the model
+model_name = "Mykes/med_tinyllama_gguf"
+filename = "med_tinyllama.gguf"
+model_path = hf_hub_download(repo_id=model_name, filename=filename)
 
+# Initialize the model
+model = Llama(model_path=model_path, n_ctx=512, n_threads=4)
 
 def respond(
     message,
@@ -15,49 +18,42 @@ def respond(
     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})
+    # Construct the prompt
+    prompt = f"{system_message}\n\n"
+    for user_msg, assistant_msg in history:
+        prompt += f"Human: {user_msg}\nAssistant: {assistant_msg}\n"
+    prompt += f"Human: {message}\nAssistant: "
 
+    # Generate response
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    for token in model(
+        prompt,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        response += token['choices'][0]['text']
+        yield response.strip()
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create the Gradio interface
 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.Textbox(value="You are a friendly medical assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=512, value=100, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
-            value=0.95,
+            value=0.9,
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
     ],
+    title="Med TinyLlama Chat",
+    description="Chat with the Med TinyLlama model for medical information.",
 )
 
-
 if __name__ == "__main__":
     demo.launch()