Update app.py

app.py

@@ -1,64 +1,51 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import time
 
-"""
-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("shaneperry0101/Health-Llama-3.2-1B")
+from transformers import AutoTokenizer
+import transformers
+import torch
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+global tokenizer, pipeline
 
-    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)",
-        ),
-    ],
+model = "shaneperry0101/Health-Llama-3.2-1B"
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
 )
 
+def chat_response(message):
+  system_message="Welcome! You're now communicating with an AI model trained to assist with information about general health disease. Feel free to ask about causes, symptoms, medications, and treatment options!"
+  prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n{message}[/INST]"
+  sequences = pipeline(
+      f'[INST] {prompt} [/INST]',
+      do_sample=True,
+      top_k=10,
+      num_return_sequences=1,
+      eos_token_id=tokenizer.eos_token_id,
+      max_length=500,
+  )
+  for seq in sequences:
+      bot_message = seq['generated_text'].replace(prompt, '').split('[/INST]')[-1]
+
+  return bot_message
+
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot(label="Personal Health Assistant")
+    msg = gr.Textbox()
+    clear = gr.ClearButton([msg, chatbot])
+
+    def respond(message, chat_history):
+        bot_message = chat_response(message)
+        chat_history.append((message, bot_message))
+        time.sleep(2)
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
 
 if __name__ == "__main__":
     demo.launch()