Update app.py

app.py

@@ -1,12 +1,10 @@
 import re
-from unsloth import FastLanguageModel
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM
 
 config = PeftConfig.from_pretrained("FlawedLLM/BhashiniLLM")
 base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit")
 model = PeftModel.from_pretrained(base_model, "FlawedLLM/BhashiniLLM")
-FastLanguageModel.for_inference(model) # Enable native 2x faster inference
 tokenizer = AutoTokenizer.from_pretrained("FlawedLLM/BhashiniLLM")
 @spaces.GPU
 def chunk_it(input_command):