From af55803d0dff9eb692c760c8d486e736c945061d Mon Sep 17 00:00:00 2001 From: Onur Gündüz Date: Sat, 27 Jun 2026 00:58:05 +0200 Subject: chore: clean up comment formatting and wording --- tests/check_tokenizer_parity.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'tests/check_tokenizer_parity.py') diff --git a/tests/check_tokenizer_parity.py b/tests/check_tokenizer_parity.py index acea177..70eea3c 100755 --- a/tests/check_tokenizer_parity.py +++ b/tests/check_tokenizer_parity.py @@ -1,11 +1,11 @@ #!/usr/bin/env python3 -"""Check the C BPE tokenizer against stored reference vectors. +"""Check the BPE tokenizer against stored reference vectors. The reference ids live in tests/test-vectors/bpe/expected.json, generated from -the Qwen tokenizer by devtools/gen_test_vectors.py. This builds the C BPE driver -(tests/tokenizer_dump), runs it against the checked-in vocab.json + merges.txt, -and compares the ids exactly. It imports no transformers and downloads no model, -so it is hermetic and fast. +the Qwen tokenizer by devtools/gen_test_vectors.py. + +This builds the C BPE driver (tests/tokenizer_dump), runs it against the checked-in +vocab.json + merges.txt, and compares the ids exactly. tests/check_tokenizer_parity.py tests/check_tokenizer_parity.py --cc clang -- cgit v1.3.1