From ee70d8ac8c50d3abf852f3820edc00f4c2df7514 Mon Sep 17 00:00:00 2001 From: Eternal Reclaimer <98760976+kyegomez@users.noreply.github.com> Date: Wed, 20 Dec 2023 23:27:42 -0500 Subject: [PATCH] Delete tokenizer.py --- tokenizer.py | 12 ------------ 1 file changed, 12 deletions(-) delete mode 100644 tokenizer.py diff --git a/tokenizer.py b/tokenizer.py deleted file mode 100644 index 9d04293..0000000 --- a/tokenizer.py +++ /dev/null @@ -1,12 +0,0 @@ -from gemini_torch.tokenizer import MultimodalSentencePieceTokenizer - -# Example usage -tokenizer_name = "hf-internal-testing/llama-tokenizer" -tokenizer = MultimodalSentencePieceTokenizer(tokenizer_name=tokenizer_name) - -# Encoding and decoding examples -encoded_audio = tokenizer.encode("Audio description", modality="audio") -decoded_audio = tokenizer.decode(encoded_audio) - -print("Encoded audio:", encoded_audio) -print("Decoded audio:", decoded_audio)