Skip to content

Suggest the Json() type for tool calling dataset format#5307

Merged
qgallouedec merged 5 commits into
huggingface:mainfrom
lhoestq:patch-3
Mar 18, 2026
Merged

Suggest the Json() type for tool calling dataset format#5307
qgallouedec merged 5 commits into
huggingface:mainfrom
lhoestq:patch-3

Conversation

@lhoestq

@lhoestq lhoestq commented Mar 18, 2026 •
edited by cursor Bot
Loading

Copy link
Copy Markdown
Member

Note

Low Risk
Low risk documentation-only change; main risk is minor confusion if users rely on the previous legacy tools JSON-string recommendation for older datasets versions.

Overview
Updates the tool-calling dataset documentation to treat get_json_schema() output as a Python dict (not a JSON string) and to store tools as a list of schemas ([json_schema]).

Adds guidance on constructing a datasets.Dataset by using the Json() feature type (or on_mixed_types="use_json") for arbitrary tool-call arguments, and documents a fallback for datasets<4.8 where tools should be stored via json.dumps(...).

Written by Cursor Bugbot for commit 24226bf. This will update automatically on new commits. Configure here.

lhoestq added 2 commits March 18, 2026 15:22
@lhoestq
Refactor JSON schema and dataset entry examples
8fc8198 
Updated JSON schema generation and dataset entry format for tools.
@lhoestq
fix quotes
875765e
@lhoestq lhoestq marked this pull request as ready for review March 18, 2026 14:24
@qgallouedec

qgallouedec commented Mar 18, 2026

Copy link
Copy Markdown
Member

thanks!

@HuggingFaceDocBuilderDev

HuggingFaceDocBuilderDev commented Mar 18, 2026

Copy link
Copy Markdown

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.

@qgallouedec qgallouedec merged commit 3972d66 into huggingface:main Mar 18, 2026
2 checks passed
qgallouedec added a commit that referenced this pull request Mar 18, 2026
@qgallouedec
Squashed commit of the following:
14dbaf1 
commit 3972d66
Author: Quentin Lhoest <42851186+lhoestq@users.noreply.github.com>
Date:   Wed Mar 18 22:26:44 2026 +0100

    Suggest the `Json()` type for tool calling dataset format (#5307)

    Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>
    Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>

commit 5c6e915
Author: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Date:   Wed Mar 18 14:55:19 2026 -0600

    Update `RewardFunc` type annotation to allow `None`values in reward list (#5297)

commit ee96845
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Wed Mar 18 17:03:54 2026 +0100

    Fix DPOTrainer collators to truncate sequences before padding (#5305)

commit 435c2ae
Author: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Date:   Wed Mar 18 08:09:42 2026 -0600

    Add guidance to avoid `hasattr` and `getattr` with defaults in `AGENTS.md` (#5294)

commit 26ce6a3
Author: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Date:   Wed Mar 18 00:44:12 2026 -0600

    Apply docstyle (#5296)

commit 52cd0cc
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Tue Mar 17 15:31:26 2026 +0100

    Fix UNEXPECTED lm_head.weight warning when loading a CausalLM as a reward model (#5295)

commit 7b42fc4
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Tue Mar 17 15:29:11 2026 +0100

    Prevent corruption of DPO VLM training if "keep_end" truncation_mode (#5286)

commit 3acb8e8
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Tue Mar 17 15:27:10 2026 +0100

    Support max_length in DPO VLM training (#5284)

commit ee339a0
Author: Carlos Miguel Patiño <carlos.patino@huggingface.co>
Date:   Tue Mar 17 14:01:44 2026 +0100

    [GKD] Buffer Implementation for Distillation Trainer (#5137)

    Co-authored-by: lewtun <lewis.c.tunstall@gmail.com>

commit d46131f
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Mon Mar 16 15:27:19 2026 +0100

    Remove custom get_train/eval_dataloader from OnlineDPO (#5291)

commit 85cf8f4
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Mon Mar 16 15:24:24 2026 +0100

    Remove TrainingArguments import from experimental trainers (#5290)

commit 91e3da0
Author: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Date:   Mon Mar 16 07:19:51 2026 -0600

    Fix `accuracy_reward` crash when called from non-main thread (#5281)

commit 4996631
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Mon Mar 16 07:44:28 2026 +0100

    Fix support for model_init_kwargs in MiniLLM when passed as CLI JSON string (#5274)

commit 5fceaa7
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Mon Mar 16 07:43:34 2026 +0100

    Simplify structured outputs logic across vLLM versions in scripts/vllm_serve (#5273)

commit 406d406
Author: casinca <47400729+casinca@users.noreply.github.com>
Date:   Sat Mar 14 04:12:49 2026 +0100

    feat(`grpo_trainer.py`): Variational Sequence-Level Soft Policy Optimization (VESPO) (#5199)

commit d0ac7ef
Author: LeonEricsson <70749762+LeonEricsson@users.noreply.github.com>
Date:   Sat Mar 14 02:53:33 2026 +0100

    Allow nullable logprobs in vLLM serve responses  (#5203)

    Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
    Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>

commit c0eabc4
Author: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Date:   Fri Mar 13 18:19:15 2026 -0600

    Change default `vllm_mode` to `"colocate"` and add v0→v1 migration guide (#5255)

    Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

commit 6c0fccd
Author: Mario Šaško <mariosasko777@gmail.com>
Date:   Sat Mar 14 00:19:38 2026 +0100

    35% faster packing + rename `bfd-requeue` to `bfd_split` (#5189)

    Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
    Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>
@albertvillanova

albertvillanova commented Mar 19, 2026

Copy link
Copy Markdown
Member

Thanks, @lhoestq, the JSON dtype will definitely help make things easier!

This was referenced Mar 19, 2026
Merged
Merged
@albertvillanova albertvillanova mentioned this pull request Mar 26, 2026
Merged
songhappy pushed a commit to songhappy/trl that referenced this pull request Apr 20, 2026
@lhoestq @qgallouedec
Suggest the Json() type for tool calling dataset format (huggingfac…
e9d8536 
…e#5307)

Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>
Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@qgallouedec qgallouedec qgallouedec approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@lhoestq @qgallouedec @HuggingFaceDocBuilderDev @albertvillanova