Test

app.py

@@ -3,20 +3,17 @@ from peft import PeftModel
 from transformers import TextStreamer
 
 # Load model directly
-from transformers import AutoModel, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 Info of how to use a model after training on hf https://huggingface.co/docs/trl/main/en/use_model
 """
 
-model_name_or_path = "unsloth/Llama-3.2-3B-Instruct"
-adapter_name = "samlama111/lora_model"
+peft_model_id = "samlama111/lora_model"
+model = AutoModelForCausalLM.from_pretrained(peft_model_id)
 
-model = AutoModel.from_pretrained(model_name_or_path)
-tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
-
-model = PeftModel.from_pretrained(model, adapter_name)
+tokenizer = AutoTokenizer.from_pretrained("samlama111/lora_model")
 
 
 def respond(