Update app.py

app.py

@@ -1,15 +1,10 @@
 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 git+https://github.com/huggingface/optimum.git")
-os.system("pip install git+https://github.com/huggingface/transformers.git")
-os.system("pip install --upgrade accelerate")
-os.system("pip install bitsandbytes")
+os.system("pip install -q flash_attn==2.7.4.post1 transformers==4.49.0 accelerate>=0.26.0")
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import re
 import os
 import torch
-import bitsandbytes
 
 hf_token = os.environ.get('hf_token')
 
@@ -19,8 +14,7 @@ model = AutoModelForCausalLM.from_pretrained(
     model_path,
     #device_map="auto",
     #torch_dtype="auto",
-    trust_remote_code=True,
-    load_in_8bit=True
+    trust_remote_code=True
 )
 tokenizer = AutoTokenizer.from_pretrained(model_path)