chore: Update model doc for code_llama by AbhishekRP2002 · Pull Request #37115 · huggingface/transformers

AbhishekRP2002 · 2025-03-30T12:56:11Z

What does this PR do?

sub part of #36979

Before submitting

This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
Did you read the contributor guideline,
Pull Request section?
Was this discussed/approved via a Github issue or the forum? 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, and
here are tips on formatting docstrings.
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.

@stevhliu

aims to handle huggingface#36979 (comment) sub part of huggingface#36979

github-actions · 2025-03-30T12:56:24Z

Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the Ready for review button (at the bottom of the PR page). This will assign reviewers and trigger CI.

HuggingFaceDocBuilderDev · 2025-03-31T20:48:46Z

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

stevhliu

Great job! 👏

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

stevhliu

Nice, just a few more comments :)

stevhliu · 2025-04-02T19:59:53Z

+## Notes

+- Infilling is only available in the 7B and 13B base models, and not in the Python, Instruct, 34B, or 70B models.
+- Use the `<FILL_ME>` token where you want your input to be filled. The tokenizer splits this token to create a formatted input string that follows the [original training pattern](https://github.com/facebookresearch/codellama/blob/cb51c14ec761370ba2e2bc351374a79265d0465e/llama/generation.py#L402). This is more robust than preparing the pattern yourself.


Put the indented code example here for <FILL_ME>:

from transformers import LlamaForCausalLM, CodeLlamaTokenizer tokenizer = CodeLlamaTokenizer.from_pretrained("meta-llama/CodeLlama-7b-hf") model = LlamaForCausalLM.from_pretrained("meta-llama/CodeLlama-7b-hf") PROMPT = '''def remove_non_ascii(s: str) -> str: """ <FILL_ME> return result ''' input_ids = tokenizer(PROMPT, return_tensors="pt")["input_ids"] generated_ids = model.generate(input_ids, max_new_tokens=128) filling = tokenizer.batch_decode(generated_ids[:, input_ids.shape[1]:], skip_special_tokens = True)[0] print(PROMPT.replace("<FILL_ME>", filling))

Implemented the suggested changes ! Thank you for assisting. @stevhliu , please lemme know if there's anything else missed from my end.

The code example here isn't indented yet. It should be formatted like below:

- some text ```py code snippet

stevhliu

Super close! Remember to mark as ready for review when you're done 🤗

stevhliu · 2025-04-03T01:15:17Z

+## Notes

+- Infilling is only available in the 7B and 13B base models, and not in the Python, Instruct, 34B, or 70B models.
+- Use the `<FILL_ME>` token where you want your input to be filled. The tokenizer splits this token to create a formatted input string that follows the [original training pattern](https://github.com/facebookresearch/codellama/blob/cb51c14ec761370ba2e2bc351374a79265d0465e/llama/generation.py#L402). This is more robust than preparing the pattern yourself.


The code example here isn't indented yet. It should be formatted like below:

- some text ```py code snippet

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

AbhishekRP2002 · 2025-04-03T05:09:55Z

Super close! Remember to mark as ready for review when you're done 🤗

Thank you ! marked the PR as Ready @stevhliu

* Update code_llama.md aims to handle huggingface#36979 (comment) sub part of huggingface#36979 * Update docs/source/en/model_doc/code_llama.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/code_llama.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/code_llama.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * make changes as per code review * chore: make the function smaller for attention mask visualizer * chore[docs]: update code_llama.md with some more suggested changes * Update docs/source/en/model_doc/code_llama.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * chore[docs] : Update code_llama.md with indentation changes --------- Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

Update code_llama.md

23b2efe

aims to handle huggingface#36979 (comment) sub part of huggingface#36979

github-actions Bot marked this pull request as draft March 30, 2025 12:56

stevhliu mentioned this pull request Mar 31, 2025

[Community contributions] Model cards #36979

Closed

stevhliu reviewed Mar 31, 2025

View reviewed changes

AbhishekRP2002 and others added 7 commits April 1, 2025 08:55

Update docs/source/en/model_doc/code_llama.md

65ceec2

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

Update docs/source/en/model_doc/code_llama.md

5aa6dbf

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

Update docs/source/en/model_doc/code_llama.md

b83c82a

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

make changes as per code review

37ad574

Merge branch 'huggingface:main' into model-card-update

6f34b03

chore: make the function smaller for attention mask visualizer

5c8e8c7

Merge branch 'huggingface:main' into model-card-update

affa590

stevhliu reviewed Apr 2, 2025

View reviewed changes

AbhishekRP2002 added 2 commits April 3, 2025 05:55

chore[docs]: update code_llama.md with some more suggested changes

2426784

Merge branch 'huggingface:main' into model-card-update

5745960

stevhliu approved these changes Apr 3, 2025

View reviewed changes

AbhishekRP2002 marked this pull request as ready for review April 3, 2025 04:37

AbhishekRP2002 and others added 3 commits April 3, 2025 10:07

Update docs/source/en/model_doc/code_llama.md

c4076d2

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

Merge branch 'huggingface:main' into model-card-update

8371117

chore[docs] : Update code_llama.md with indentation changes

9b92e8f

stevhliu merged commit b552708 into huggingface:main Apr 3, 2025
10 checks passed

stevhliu mentioned this pull request Jun 30, 2025

Improve Code Llama documentation with explanations and helpful links #39113

Closed

5 tasks

Conversation

AbhishekRP2002 commented Mar 30, 2025 • edited by stevhliu Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Before submitting

Who can review?

Uh oh!

github-actions Bot commented Mar 30, 2025

Uh oh!

HuggingFaceDocBuilderDev commented Mar 31, 2025

Uh oh!

stevhliu left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

stevhliu left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

stevhliu Apr 2, 2025

Choose a reason for hiding this comment

Uh oh!

AbhishekRP2002 Apr 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

stevhliu Apr 3, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

stevhliu left a comment

Choose a reason for hiding this comment

Uh oh!

stevhliu Apr 3, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

AbhishekRP2002 commented Apr 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

AbhishekRP2002 commented Mar 30, 2025 •

edited by stevhliu

Loading

AbhishekRP2002 Apr 3, 2025 •

edited

Loading

AbhishekRP2002 commented Apr 3, 2025 •

edited

Loading