Update app.py

app.py

@@ -6,7 +6,7 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
 import time
 
-model_id = "facebook/opt-1.3b"
+model_id = "facebook/opt-6.7b"
 assistant_id = "facebook/opt-125m"
 
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
@@ -56,7 +56,7 @@ def reset_textbox():
 with gr.Blocks() as demo:
     gr.Markdown(
         "# 🤗 Assisted Generation Demo\n"
-        f"- Model: {model_id} (BF16, ~3GB)\n"
+        f"- Model: {model_id} (BF16, ~14GB)\n"
         f"- Assistant Model: {assistant_id} (BF16, ~0.3GB)\n"
         "- Running on a T4 GPU\n"
         "- Best results are obtained when the model size difference in parameters is >10x"