Update app.py

app.py

@@ -3,26 +3,15 @@ import gradio as gr
 from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import transformers
-import bitsandbytes
-import accelerate
 
 
 adapters_name = "1littlecoder/mistral-7b-mj-finetuned"
 model_name = "bn22/Mistral-7B-Instruct-v0.1-sharded"
 
-bnb_config = transformers.BitsAndBytesConfig(
-    load_in_8bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
+
 
 model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    load_in_8bit=True,
-    torch_dtype=torch.bfloat16,
-    quantization_config=bnb_config,
-    device_map='auto'
+    model_name
 )
 model = PeftModel.from_pretrained(model, adapters_name)