Update app.py

app.py

@@ -9,9 +9,9 @@ from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
 from llama_cpp import LlamaRAMCache
 
-hf_hub_download(repo_id="TheBloke/Llama-2-7B-chat-GGML", filename="llama-2-7b-chat.ggmlv3.q4_K_M.bin", local_dir=".")
+hf_hub_download(repo_id="TheBloke/Llama-2-7b-Chat-GGUF", filename="llama-2-7b-chat.Q4_K_M.gguf", local_dir=".")
 
-llm = Llama(model_path="./llama-2-7b-chat.ggmlv3.q4_K_M.bin", rms_norm_eps=1e-5)
+llm = Llama(model_path="./llama-2-7b-chat.Q4_K_M.gguf", rms_norm_eps=1e-5)
 
 cache = LlamaRAMCache(capacity_bytes=2 << 30)
 
@@ -112,7 +112,7 @@ seafoam = SeafoamCustom()
 with gr.Blocks(theme=seafoam, analytics_enabled=False, css=css) as demo:
     with gr.Column():
         gr.Markdown(
-            """ ## Meta's Llama 2 7B-chat GGML
+            """ ## Meta's Llama 2 7B-chat
             
             4bit (q4_K_M)