Hugging Face's logo

Spaces:
MatrixStudio
/
Qwen-7B-gguf-API
Running

App Files Community
Alex0007 commited on
Commit
af84458
·
verified ·
1 Parent(s): 71b6650

Update config.toml

Browse files
Files changed (1) hide show
  1. config.toml +1 -1
config.toml CHANGED
@@ -1,2 +1,2 @@
1
  model="/app/llama.cpp/models/7B/qwen7b-q4_0.gguf"
2
- n_threads="12"
 
1
  model="/app/llama.cpp/models/7B/qwen7b-q4_0.gguf"
2
+ n_threads="1"