Update app.py

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import torch
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
+pipe = pipeline("text-generation", model="meta-llama/Llama-2-70b-chat-hf", torch_dtype=torch.bfloat16, device_map="auto")
 
 def model_generate(text):
     # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
@@ -18,6 +18,4 @@ def model_generate(text):
     return outputs[0]["generated_text"]
 
 iface = gr.Interface(fn=model_generate, inputs=["text"], outputs="text")
-iface.launch()
-
-gr.load("models/TinyLlama/TinyLlama-1.1B-Chat-v1.0").launch()
+iface.launch()