Update app.py

app.py

@@ -23,11 +23,11 @@ from espnet2.bin.tts_inference import Text2Speech
 
 repo_id = "Sosaka/Vicuna-7B-4bit-ggml"
 filename = "vicuna-7B-1.1-ggml_q4_0-ggjt_v3.bin"
-cache_dir="~/.cache/huggingface"
-hf_hub_download(repo_id=repo_id, filename=filename, cache_dir=cache_dir)
+cache_dir="~/.cache/huggingface/hub"
+#hf_hub_download(repo_id=repo_id, filename=filename, cache_dir=cache_dir)
 '''
 llm = Llama(
-      model_path="~/.cache/huggingface/vicuna-7B-1.1-ggml_q4_0-ggjt_v3.bin",
+      model_path="~/.cache/huggingface/hub/vicuna-7B-1.1-ggml_q4_0-ggjt_v3.bin",
       n_gpu_layers=-1, # Uncomment to use GPU acceleration
       # seed=1337, # Uncomment to set a specific seed
       n_ctx=4096, # Uncomment to increase the context window