llama-cpp-python-cuda-gradio

Runtime error

radames commited on Aug 20, 2023

Commit

2414e27

1 Parent(s): 7794339

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -12,7 +12,7 @@ llm = Llama(
         filename="llama-2-7b-chat.ggmlv3.q5_0.bin",
     ),
     n_ctx=2048,
-    n_gpu_layers=5000, # change n_gpu_layers if you have more or less VRAM
 )
 history = []

         filename="llama-2-7b-chat.ggmlv3.q5_0.bin",
     ),
     n_ctx=2048,
+    n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM
 )
 history = []