Update app.py

app.py

@@ -7,7 +7,6 @@ import transformers
 
 adapters_name = "1littlecoder/mistral-7b-mj-finetuned"
 model_name = "bn22/Mistral-7B-Instruct-v0.1-sharded"
-device = "cuda"
 
 bnb_config = transformers.BitsAndBytesConfig(
     load_in_8bit=True,
@@ -76,7 +75,6 @@ def generate(
 
     encoded = tokenizer(formatted_prompt, return_tensors="pt", add_special_tokens=False)
     model_input = encoded
-    model.to(device)
     generated_ids = model.generate(**model_input, max_new_tokens=200, do_sample=True)