Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

Choosing-a-trainer table documents KTO rows as {prompt, response, label}, but the KTO loader requires a completion column (F-W1-DOCS-TRAIN-02)

Open Beginner friendly
  • Is something wrong?
#885 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
75/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Active
Tech stack
markdown, python
Domain
documentation, machine-learning

Research direction

Start with the KTO row at line 51 of docs/usermanuals/en/concepts/choosing-trainer.md, then check the KTO column requirements in the _validate_trainer_columns branch of forgelm/data.py around lines 600-607. Change the row to {prompt, completion, label: bool} in the English page and in the Turkish mirror at docs/usermanuals/tr/concepts/choosing-trainer.md line 51. Leave the SFT row at line 49 for #403. Done when both languages match the loader and the KTO page.

Written by the indexing model from the issue text.

Description

documentation good first issue severity: medium source: review-2026-09 wave: 3

Wave 3 · group W3 Docs · highest severity Medium · 1 finding(s) · effort docs fix

Summary

The "What to look at in your data" table says {prompt, response, label: bool} rows mean KTO. The KTO loader requires completion and label and stops with a KeyError on response, so data shaped the way the page recommends does not load.

Primary finding

F-W1-DOCS-TRAIN-02 — The choosing-a-trainer table names the wrong KTO answer column

severity Medium · confidence high · checked against the loader

What happens. docs/usermanuals/en/concepts/choosing-trainer.md:51 and the Turkish mirror at the same line. _validate_trainer_columns raises KeyError: KTO trainer requires 'completion' and 'label' (boolean) columns … (forgelm/data.py:600-607). The row above it (:49, {prompt, completion} → SFT) is the SFT-format defect tracked in #403; that issue now lists this page too.

Where.

Evidence (re-verified on 2026-10-09).

  • The KTO branch of _validate_trainer_columns names only completion and label; both table rows are unchanged on development.

Recommended fix. Change the KTO row to {prompt, completion, label: bool} in both languages, matching the KTO page and the loader. Settle the SFT row (:49) with whatever #403 decides for the SFT format.

Related. #403 — the SFT row of the same table; fix both rows together if the PRs overlap.

Acceptance criteria

  • Every data shape in the table loads with the trainer it recommends.
  • Documentation listed above is corrected in English and in its Turkish mirror in the same PR.
  • The finding is resolved or explicitly closed with a reason.

Found by the September 2026 independent review of ForgeLM against commit cab2947 and re-verified against development at f94595f on 2026-10-09. Code links point at cab2947; line numbers may have moved since. Finding IDs (F-W1-…) are stable references for this backlog.

Dominant language
Python
Stars
9
Forks
1
Avg merge
8h 10m
Merged PRs (30d)
5

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from HodeTech/ForgeLM

All issues in HodeTech/ForgeLM

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.