feat: cache huggingface gpt2 tokenizer files (#1138)

877da82b · takatost · GitHub · 66376290 · 877da82b
Unverified Commit 877da82b authored Sep 10, 2023 by takatost Committed by GitHub Sep 10, 2023
Show whitespace changes
Inline Side-by-side

Showing with 3 additions and 1 deletion

Dockerfile api/Dockerfile +3 -1

No files found.
--- a/api/Dockerfile
+++ b/api/Dockerfile
@@ -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