Update app.py

app.py

@@ -8,7 +8,7 @@ from huggingface_hub import hf_hub_download #load from huggingfaces
 
 
 llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/orca_mini_3B-GGML", filename="orca-mini-3b.ggmlv3.q4_1.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
-
+print ("repo_id", repo_id)
 history = []
 
 pre_prompt = " The user and the AI are having a conversation : "
@@ -36,8 +36,8 @@ def generate_text(input_text, history):
 
 
 demo = gr.ChatInterface(generate_text,
-    title="Yes Man",
-    description="Ask Yes Man any question",
+    title="LLM on CPU",
+    description="Running LLM with https://github.com/abetlen/llama-cpp-python. btw the text streaming thing was the hardest thing to impliment",
     examples=["Hello", "Am I cool?", "Are tomatoes vegetables?"],
     cache_examples=True,
     retry_btn=None,