normal chatbot, not trained on med info

app.py

@@ -1,50 +1,65 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
-import torch
 
+"""
+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")
 
-class Assistant:
-    def __init__(self):
-        model_name = "ruslanmv/Medical-Llama3-8B"
-        device_map = 'auto'
-        # bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.float16,)
-        # self.model = AutoModelForCausalLM.from_pretrained( model_name,quantization_config=bnb_config, trust_remote_code=True,use_cache=False,device_map=device_map)
-        self.model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True,use_cache=False,device_map=device_map)
-        
-        self.tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-        self.tokenizer.pad_token = self.tokenizer.eos_token
-
-
-    def respond(
-        self,
-        message
+
+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,
     ):
-        sys_message = ''' 
-        You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
-        provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
-        '''   
-        messages = [{"role": "system", "content": sys_message}, {"role": "user", "content": message}]
-        
-        # Applying chat template
-        prompt = self.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-        inputs = self.tokenizer(prompt, return_tensors="pt").to("cuda")
-        outputs = self.model.generate(**inputs, max_new_tokens=100, use_cache=True)
-        
-        # Extract and return the generated text, removing the prompt
-        response_text = self.tokenizer.batch_decode(outputs)[0].strip()
-        answer = response_text.split('<|im_start|>assistant')[-1].strip()
-        return answer
+        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
 """
-assistant = Assistant()
-
 demo = gr.ChatInterface(
-    assistant.respond
+    respond,
+    additional_inputs=[
+        gr.Textbox(value= ''' 
+        You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
+        provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
+        ''', 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)",
+        ),
+    ],
 )