From 877da82b069dc7644d55cb02424788f73ea684a2 Mon Sep 17 00:00:00 2001
From: takatost <takatost@users.noreply.github.com>
Date: Sun, 10 Sep 2023 12:16:21 +0800
Subject: [PATCH] feat: cache huggingface gpt2 tokenizer files (#1138)

---
 api/Dockerfile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/api/Dockerfile b/api/Dockerfile
index 4bd1e68db7..824506c46b 100644
--- a/api/Dockerfile
+++ b/api/Dockerfile
@@ -26,7 +26,7 @@ EXPOSE 5001
 
 WORKDIR /app/api
 
-RUN apt-get update \ 
+RUN apt-get update \
     && apt-get install -y --no-install-recommends bash curl wget vim nodejs \
     && apt-get autoremove \
     && rm -rf /var/lib/apt/lists/*
@@ -34,6 +34,8 @@ RUN apt-get update \
 COPY --from=base /pkg /usr/local
 COPY . /app/api/
 
+RUN python -c "from transformers import GPT2TokenizerFast; GPT2TokenizerFast.from_pretrained('gpt2')"
+
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh