1 files changed, 25 insertions, 16 deletions
diff --git a/tests/test-tokenizer-0-bpe.py b/tests/test-tokenizer-0-bpe.py
index 33a27244..6b70ad03 100644
--- a/tests/test-tokenizer-0-bpe.py
+++ b/tests/test-tokenizer-0-bpe.py
@@ -7,15 +7,20 @@
 #   python3 tests/test-tokenizer-0-bpe.py ~/Data/huggingface/deepseek-coder-6.7b-instruct/
 #
 
+import logging
 import argparse
 
 from transformers import AutoTokenizer
 
+logger = logging.getLogger("test-tokenizer-0-bpe")
+
 parser = argparse.ArgumentParser()
 parser.add_argument("dir_tokenizer", help="directory containing 'tokenizer.model' file")
 parser.add_argument("--fname-tok",   help="path to a text file to tokenize")
-args = parser.parse_args()
+parser.add_argument("--verbose", action="store_true", help="increase output verbosity")
 
+args = parser.parse_args()
+logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
 dir_tokenizer = args.dir_tokenizer
 
 tokenizer = AutoTokenizer.from_pretrained(dir_tokenizer)
@@ -64,30 +69,34 @@ tests = [
 ]
 
 for text in tests:
-    print('text: ', text)
-    print(tokenizer.encode(text))
-    print(tokenizer.decode(tokenizer.encode(text)))
+    logger.info(f"text: {text}")
+    logger.info(tokenizer.encode(text))
+    logger.info(tokenizer.decode(tokenizer.encode(text)))
 
-print("\n\ntests for C++:\n")
+logger.info("tests for C++:")
 for text in tests:
     res = tokenizer.encode(text)
 
+    # Modify text representation for logging
     k = text.replace('\n', '\\n')
     k = k.replace('\t', '\\t')
     k = '"' + k + '"'
-    print("{ %-24s, { " % k, end='')
+
+    # Log the modified text and its encoding
+    log_message = "{ %-24s, { " % k
     for x in res:
-        print("%7d," % x, end='')
-    print(" }, },")
+        log_message += "%7d," % x
+    log_message += " }, },"
+    logger.info(log_message)
 
-print(tokenizer.encode('hello'))
-print(tokenizer.encode('world'))
-print(tokenizer.encode(' world'))
-print(tokenizer.encode('hello world'))
+logger.info(tokenizer.encode('hello'))
+logger.info(tokenizer.encode('world'))
+logger.info(tokenizer.encode(' world'))
+logger.info(tokenizer.encode('hello world'))
 
 fname_tok = args.fname_tok
 if fname_tok:
-    print('tokenizing file: ', fname_tok)
+    logger.info(f"tokenizing file: {fname_tok}")
     fname_out = fname_tok + '.tok'
     with open(fname_tok, 'r', encoding='utf-8') as f:
         lines = f.readlines()
@@ -112,6 +121,6 @@ if fname_tok:
                 # else:
                 #     f.write(str(x) + ' \'' + tokenizer.decode(x) + '\'\n')
                 f.write(str(x) + ' \'' + tokenizer.decode(x).strip() + '\'\n')
-        print('len(res): ', len(res))
-        print('len(lines): ', len(lines))
-    print('results written to: ', fname_out)
+        logger.info(f"len(res): {len(res)}")
+        logger.info(f"len(lines): {len(lines)}")
+    logger.info(f"results written to: {fname_out}")