From 91111a0dc2936741631bdd3c2be8fd354ac4c0e3 Mon Sep 17 00:00:00 2001 From: Diwank Singh Tomer Date: Thu, 23 Nov 2023 03:41:05 -0800 Subject: [PATCH] Fix missing `trust_remote_code` flag for AutoTokenizer in utils.peft (#1270) Peft loading function was missing the `trust_remote_code=trust_remote_code` argument causing the custom tokenizer code to be not found. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. @Narsil --- server/text_generation_server/utils/peft.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/utils/peft.py b/server/text_generation_server/utils/peft.py index e37447dc..d37e8940 100644 --- a/server/text_generation_server/utils/peft.py +++ b/server/text_generation_server/utils/peft.py @@ -38,7 +38,7 @@ def download_and_unload_peft(model_id, revision, trust_remote_code): os.makedirs(model_id, exist_ok=True) cache_dir = model_id logger.info(f"Saving the newly created merged model to {cache_dir}") - tokenizer = AutoTokenizer.from_pretrained(base_model_id) + tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=trust_remote_code) model.save_pretrained(cache_dir, safe_serialization=True) model.config.save_pretrained(cache_dir) tokenizer.save_pretrained(cache_dir)