Skip to content

[CodeLlamaTokenizer] Nit, update __init__ to make sure the AddedTokens are not normalized because they are special#27359

Merged
ArthurZucker merged 4 commits intomainfrom
nit-codellama
Nov 9, 2023
Merged

[CodeLlamaTokenizer] Nit, update __init__ to make sure the AddedTokens are not normalized because they are special#27359
ArthurZucker merged 4 commits intomainfrom
nit-codellama

Conversation

@ArthurZucker
Copy link
Copy Markdown
Collaborator

@ArthurZucker ArthurZucker commented Nov 8, 2023

What does this PR do?

Bridges the gap between the slow and fast version follow the updates in #26570 (similar updates were done to Llama)

@HuggingFaceDocBuilderDev
Copy link
Copy Markdown

HuggingFaceDocBuilderDev commented Nov 8, 2023

The documentation is not available anymore as the PR was closed or merged.

@ArthurZucker ArthurZucker marked this pull request as ready for review November 9, 2023 08:24
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"hf-internal-testing/llama-code-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer.model",
"codellama/CodeLlama-34b-Instruct-hf": "https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf/resolve/main/tokenizer.model",
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove these three lines and we can merge :)

(These are just here for backwards-compatibility)

Copy link
Copy Markdown
Member

@LysandreJik LysandreJik left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

great

@ArthurZucker ArthurZucker merged commit 085ea7e into main Nov 9, 2023
@ArthurZucker ArthurZucker deleted the nit-codellama branch November 9, 2023 09:15
EduardoPach pushed a commit to EduardoPach/transformers that referenced this pull request Nov 19, 2023
…ens are not normalized because they are special (huggingface#27359)

* make sure tokens are properly initialized for codellama slow

* add m ore pretrained models

* style

* test more tokenizers checkpoints
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants