Update app.py

Try PEFT for fine tuned model

app.py

@@ -7,6 +7,7 @@ import spaces
 import torch
 from huggingface_hub import InferenceClient
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from peft import AutoPeftModelForCausalLM
 
 MAX_MAX_NEW_TOKENS = 512
 DEFAULT_MAX_NEW_TOKENS = 512