app.py done!

app.py

@@ -0,0 +1,21 @@
+import torch
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoModel
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-13b-chat-hf",trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-13b-chat-hf", trust_remote_code=True).float()
+
+
+def chat(message,history):
+    for response,history in model.stream_chat(tokenizer,message,history,max_length=2048,top_p=0.7,temperature=1):
+        yield response
+
+gr.ChatInterface(chat,
+                 title="llama2 (Play AI chat at aironheart.com For FREE!)",
+                description="""
+Hi guys! I am a solo developer and I made an app: __ProChat__.  
+
+                 """,
+                 ).queue(1).launch()