Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoModel,AutoConfig, AutoTokenizer
+from transformers import AutoModel, AutoTokenizer
 import torch
 
 # Initialize Hugging Face Inference API client
@@ -9,8 +9,7 @@ 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)
-config = AutoConfig.from_pretrained(local_model_name)
-model = AutoModel.from_pretrained(local_model_name, config=config, trust_remote_code=True)
+model = AutoModel.from_pretrained(local_model_name, trust_remote_code=True)
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
@@ -40,7 +39,7 @@ def generate_response(
             response += token
             yield response
     else:
-        input_text = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
+        input_text = tokenizer(messages, return_tensors="pt").to(device)
         output = model.generate(input_text, max_length=max_tokens, temperature=temperature, top_p=top_p)
         response = tokenizer.decode(output[0], skip_special_tokens=True)
         yield response