Update app.py

app.py

@@ -1,9 +1,9 @@
+import spaces
 from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
 import torch
 import gradio as gr
 import random
 from textwrap import wrap
-import spaces
 
 def wrap_text(text, width=90):
     lines = text.split('\n')
@@ -51,7 +51,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id = model_id, trust_remote_code
 # Specify the configuration class for the model
 #model_config = AutoConfig.from_pretrained(base_model_id)
 
-model = MistralForCaumodel = AutoModelForCausalLM.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id , torch_dtype=torch.float16 , device_map= "auto" )
 
 class ChatBot:
     def __init__(self):
@@ -64,7 +64,7 @@ class ChatBot:
 
     def predict(self, user_input, system_prompt="You are an expert medical analyst:"):
         # Combine the user's input with the system prompt
-        formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"
+        formatted_input = f"<s> [INST] {example_instruction} [/INST] {example_answer}</s> [INST] {system_prompt} [/INST]"
 
         # Encode the formatted input using the tokenizer
         user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")