# Daniel van Strien trains a 194M GLiNER2 model to suggest Hugging Face dataset task tags

Trained on Hugging Face Jobs for about $1.50, the model proposes a task tag and probability from a dataset's column names and first row. Daniel van Strien says 17 minutes of fine-tuning raised its first-suggestion match with an owner's tag from 10% to 69%.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:32:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/9e8b0d37722245e3a4e1418a.html

Content language: en
Localization state: sameLanguage

Source: Daniel van Strien · Published 9/23/2026, 10:30:22

Daniel van Strien trained a Jev-style classifier on Hugging Face Jobs for about $1.50. It is a 194M GLiNER2 model that suggests task tags for any Hugging Face Hub dataset from its column names and first row, and returns a label with a probability.

He reports that GLiNER2's first zero-shot suggestion matched an owner's tag 10% of the time, and 69% after 17 minutes of fine-tuning. The fine-tuned model runs on a free CPU in about a second. He says owners' tags are noisy, so some answers counted as wrong are tags the owner left out.

The recipe is open: one hf jobs command trains the same kind of model on a user's own labels. The README example, using book titles, runs in about two minutes for about $0.02. The demo is the [hub-task-tagger Space](http://huggingface.co/spaces/davanstrien/hub-task-tagger), and the recipe is the [uv-scripts classification dataset](http://huggingface.co/datasets/uv-scripts/classification).

Tags: GLiNER2, Hugging Face, Fine-tuning, Dataset tagging

[View original post](https://x.com/vanstriendaniel/status/2102728964477247964)