Update app.py

app.py

@@ -1,8 +1,12 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import os
 
-client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1", token=os.getenv("HF_TOKEN"))
+tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
+model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
+
+#client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1", token=os.getenv("HF_TOKEN"))
 
 #Dynamic prompt builder based on CEFR level
 def level_to_prompt(level):