# Knowledgator/GLiFormer

> A framework for training and running generalist multitask transformer encoders that extract entities, relations, classifications, and structured records from text, documents, images, and audio. Built on GLiNER, it lets you specify labels and extraction schemas at inference time.

- Magnitude: 0.0 out of 10 — Steady
- Stars: 127 total · +0 stars on 2026-09-28 (UTC), ≈ 0 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-11 · Last push: 2026-09-15
- GitHub: https://github.com/Knowledgator/GLiFormer · Homepage: https://docs.knowledgator.com/docs/frameworks/gliformer/ · Page: https://gitnova.dev/en/r/Knowledgator/GLiFormer

## Useful for

- Extract named entities from text by specifying label types at inference time
- Build nested company → departments → employees records from unstructured text
- Fine-tune the model on your own annotations while freezing selected components

## Why it’s here

- The repository is 17 days old and already has 127 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 11
- Issues and pull requests: 4
- Watchers: 0
- Average over the last week: 1 per day
- Usual pace: 8 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 13 days

09-16 1.9, 09-17 1.9, 09-18 1.8, 09-19 1.4, 09-20 1.5, 09-21 1.7, 09-22 1.2, 09-23 1.0, 09-24 0.5, 09-25 0.1, 09-26 0.1, 09-27 0.1, 09-28 0.0

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-28 00:05 UTC, updated every 30 minutes.