Taimwe commited on
Commit
a3fc135
·
verified ·
1 Parent(s): 415d46e

Fix PEP 723 blank line

Browse files
Files changed (1) hide show
  1. quantise_securecoder.py +3 -0
quantise_securecoder.py CHANGED
@@ -5,6 +5,9 @@
5
  # "llama-cpp-python",
6
  # ]
7
  # ///
 
 
 
8
  """Download the merged SecureCoder safetensors repo, convert to GGUF via
9
  llama.cpp's convert_hf_to_gguf.py, and quantise to Q4_K_M. Runs on
10
  cpu-performance (no GPU needed for the conversion path).
 
5
  # "llama-cpp-python",
6
  # ]
7
  # ///
8
+
9
+
10
+
11
  """Download the merged SecureCoder safetensors repo, convert to GGUF via
12
  llama.cpp's convert_hf_to_gguf.py, and quantise to Q4_K_M. Runs on
13
  cpu-performance (no GPU needed for the conversion path).