From 330382cc39eeebd1d4dbf66a57327347cfe9918b Mon Sep 17 00:00:00 2001 From: Mengwei Liu Date: Wed, 9 Apr 2025 13:24:24 -0700 Subject: [PATCH] Fix tokenizer convert in xnnpack_README.md (#10003) As titled. (cherry picked from commit 20c704739baaf1b4d7381e61270cd680b5728fa6) --- .../android/LlamaDemo/docs/delegates/xnnpack_README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/demo-apps/android/LlamaDemo/docs/delegates/xnnpack_README.md b/examples/demo-apps/android/LlamaDemo/docs/delegates/xnnpack_README.md index 61926246470..4a00ee88380 100644 --- a/examples/demo-apps/android/LlamaDemo/docs/delegates/xnnpack_README.md +++ b/examples/demo-apps/android/LlamaDemo/docs/delegates/xnnpack_README.md @@ -103,7 +103,7 @@ You may wonder what the ‘--metadata’ flag is doing. This flag helps export t * Convert tokenizer for Llama 2 and Llava (skip this for Llama 3.x) ``` -python -m extension.llm.tokenizer.tokenizer -t tokenizer.model -o tokenizer.bin +python -m pytorch_tokenizers.tools.llama2c.convert -t tokenizer.model -o tokenizer.bin ``` ### For LLaVA model