Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModel,AutoConfig, AutoTokenizer
 import torch
 
 # Initialize Hugging Face Inference API client
@@ -9,7 +9,8 @@ hf_client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 # Load the second model
 local_model_name = "codewithdark/latent-recurrent-depth-lm"
 tokenizer = AutoTokenizer.from_pretrained(local_model_name)
-model = AutoModelForCausalLM.from_pretrained(local_model_name)
+config = AutoConfig.from_pretrained(local_model_name)
+model = AutoModel.from_pretrained(local_model_name, config=config)
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)