Zedel17 commited on
Commit
b09762c
·
1 Parent(s): ca8f246

change number of threads

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -22,7 +22,7 @@ print("Loading GGUF model with llama-cpp-python...")
22
  llm = Llama(
23
  model_path=model_path,
24
  n_ctx=2048,
25
- n_threads=2, # HF Spaces typically have 2 vCPUs
26
  n_gpu_layers=0
27
  )
28
  print("Model loaded successfully!")
 
22
  llm = Llama(
23
  model_path=model_path,
24
  n_ctx=2048,
25
+ n_threads=8, # HF Spaces typically have 2 vCPUs
26
  n_gpu_layers=0
27
  )
28
  print("Model loaded successfully!")