Update app.py

app.py

@@ -5,10 +5,14 @@ from pptx import Presentation
 from pptx.util import Inches, Pt
 import os
 import io
+from huggingface_hub import InferenceClient
+
+# Initialize the client
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 @st.cache_resource
 def load_model():
-    model_name = "meta-llama/Llama-2-7b-chat-hf"
+    model_name = "Mixtral-8x7B-Instruct-v0.1"
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
     return tokenizer, model