From d974aed5671e6a69a68348f17a926848c98490fe Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Sat, 4 May 2024 07:58:39 +0300
Subject: [PATCH] convert : print -> logging

ggml-ci
---
 convert-hf-to-gguf-update.py | 32 ++++++++++++++++----------------
 convert-hf-to-gguf.py        |  2 +-
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/convert-hf-to-gguf-update.py b/convert-hf-to-gguf-update.py
index 82a65fd7e..2b08b8505 100644
--- a/convert-hf-to-gguf-update.py
+++ b/convert-hf-to-gguf-update.py
@@ -159,8 +159,8 @@ src_func = f"""
         chktok = tokenizer.encode(chktxt)
         chkhsh = sha256(str(chktok).encode()).hexdigest()
 
-        print(f"chktok: {{chktok}}")
-        print(f"chkhsh: {{chkhsh}}")
+        logger.debug(f"chktok: {{chktok}}")
+        logger.debug(f"chkhsh: {{chkhsh}}")
 
         res = None
 
@@ -169,22 +169,22 @@ src_func = f"""
         #       don't edit the hashes manually!
 {src_ifs}
         if res is None:
-            print("\\n")
-            print("**************************************************************************************")
-            print("** WARNING: The BPE pre-tokenizer was not recognized!")
-            print("**          There are 2 possible reasons for this:")
-            print("**          - the model has not been added to convert-hf-to-gguf-update.py yet")
-            print("**          - the pre-tokenization config has changed upstream")
-            print("**          Check your model files and convert-hf-to-gguf-update.py and update them accordingly.")
-            print("** ref:     https://github.com/ggerganov/llama.cpp/pull/6920")
-            print("**")
-            print(f"** chkhsh:  {{chkhsh}}")
-            print("**************************************************************************************")
-            print("\\n")
+            logger.warning("\\n")
+            logger.warning("**************************************************************************************")
+            logger.warning("** WARNING: The BPE pre-tokenizer was not recognized!")
+            logger.warning("**          There are 2 possible reasons for this:")
+            logger.warning("**          - the model has not been added to convert-hf-to-gguf-update.py yet")
+            logger.warning("**          - the pre-tokenization config has changed upstream")
+            logger.warning("**          Check your model files and convert-hf-to-gguf-update.py and update them accordingly.")
+            logger.warning("** ref:     https://github.com/ggerganov/llama.cpp/pull/6920")
+            logger.warning("**")
+            logger.warning(f"** chkhsh:  {{chkhsh}}")
+            logger.warning("**************************************************************************************")
+            logger.warning("\\n")
             raise NotImplementedError("BPE pre-tokenizer was not recognized - update get_vocab_base_pre()")
 
-        print(f"tokenizer.ggml.pre: {{repr(res)}}")
-        print(f"chkhsh: {{chkhsh}}")
+        logger.debug(f"tokenizer.ggml.pre: {{repr(res)}}")
+        logger.debug(f"chkhsh: {{chkhsh}}")
 
         return res
 """
diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py
index f570e2c46..88c16676b 100755
--- a/convert-hf-to-gguf.py
+++ b/convert-hf-to-gguf.py
@@ -327,7 +327,7 @@ class Model(ABC):
             logger.warning("\n")
             raise NotImplementedError("BPE pre-tokenizer was not recognized - update get_vocab_base_pre()")
 
-        logger.debug(f"tokenizer.ggml.pre: {res}")
+        logger.debug(f"tokenizer.ggml.pre: {repr(res)}")
         logger.debug(f"chkhsh: {chkhsh}")
 
         return res