Update app.py

app.py

@@ -21,9 +21,11 @@ if __name__ == "__main__":
 
     print(f"Number of CPU cores: {num_cores}")
     print(f"Number of threads available to the current process: {num_threads}")
-url = 'https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q2_K.bin'
-filename = wget.download(url)
-llm2 = Llama(model_path=filename, seed=random.randint(1, 2**31), lora_path="ggml-adapter-model (1).bin", use_mlock=True, n_threads=2)
+#url = 'https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/resolve/main/llama-2-7b-chat.ggmlv3.q2_K.bin'
+#filename = wget.download(url)
+model_path= hf_hub_download(repo_id="TheBloke/llama2-7b-chat-codeCherryPop-qLoRA-GGML", filename="llama-2-7b-chat-codeCherryPop.ggmlv3.q2_K.bin"), n_ctx=2048, n_threads=2) #download model from hf/ n_ctx=2048 for high ccontext length
+
+llm2 = Llama(model_path=model_path, seed=random.randint(1, 2**31), lora_path="ggml-adapter-model (1).bin", use_mlock=True, n_threads=2)
 filename = wget.download(url)
 theme = gr.themes.Soft(
     primary_hue=gr.themes.Color("#ededed", "#fee2e2", "#fecaca", "#fca5a5", "#f87171", "#ef4444", "#dc2626", "#b91c1c", "#991b1b", "#7f1d1d", "#6c1e1e"),