Update app.py

app.py

@@ -1,6 +1,5 @@
 import os
 os.system("pip install -q flash_attn==2.7.4.post1 transformers==4.49.0 accelerate>=0.26.0")
-os.system("pip install mlx-lm")
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import re
@@ -9,7 +8,7 @@ import torch
 from mlx_lm import load, generate
 
 hf_token = os.environ.get('hf_token')
-"""
+
 model_path= 'microsoft/Phi-4-mini-instruct'
 
 model = AutoModelForCausalLM.from_pretrained(
@@ -19,9 +18,6 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True
 )
 tokenizer = AutoTokenizer.from_pretrained(model_path)
-"""
-model, tokenizer = load("mlx-community/Phi-4-mini-instruct-8bit")
-
 
 def make_prompt(sentence):
     prompt = ("""