Update app.py

app.py

@@ -7,7 +7,6 @@ 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
@@ -20,7 +19,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 if torch.cuda.is_available():
     #model_id = "Qwen/Qwen2.5-7B-Instruct"
     model_id = "BenBranyon/sumbot7b"
-    model = AutoPeftModelForCausalLM.from_pretrained(model_id, device_map="auto")
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False