Update app.py

app.py

@@ -1,8 +1,12 @@
 import gradio as gr
-from huggingface_hub import hf_hub_download
+import time
+import ctypes #to run on C api directly 
+import llama_cpp
 from llama_cpp import Llama
+from huggingface_hub import hf_hub_download #load from huggingfaces 
 
-llm = Llama(model_path=hf_hub_download(repo_id="TheBloke/airoboros-l2-13b-gpt4-m2.0-GGML", filename="airoboros-l2-13b-gpt4-m2.0.ggmlv3.q6_K.bin"), n_ctx=2048)
+
+llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/airoboros-l2-13b-gpt4-m2.0-GGML", filename="airoboros-l2-13b-gpt4-m2.0.ggmlv3.q6_K.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
 
 history = []
 history.append(["Hi there!", "Hello, how can I help you?"])
@@ -30,6 +34,3 @@ demo.launch()
 
 
 
-
-
-