Getting started with GLiNER2.5-Decide in a Colab notebook

Melvin Vivas · X post · 2026-09-25 · Open on X

Topics: LLM Fundamentals, AI Dev Tools & Productivity · Level: intermediate

Summary

Melvin Vivas shares a Google Colab notebook for trying Fastino Labs' GLiNER2.5-Decide. This is a 340M-parameter, open-weight, encoder-based decision model for fast, deterministic classification. The notebook's examples run on CPU or GPU and are in his notebooks repo.

Key points

• GLiNER2.5-Decide is a 340M-parameter, open-weight, encoder-based decision model from Fastino Labs.
• It is built for fast, deterministic classification, not free-form generation.
• You give it user-defined typed questions and rules. It decodes all the answers together in one pass.
• The creator's Colab notebook runs the examples on either CPU or GPU.
• The donvito/notebooks repo collects Colab notebooks for fine-tuning and running local models.

Resources mentioned

• donvito/notebooks · repo · github.com · free
  The creator's notebooks for fine-tuning and running local models, which you can run in Google Colab, including a GLiNER2.5-Decide intent classification example.
  Also in: Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes), Free Colab Notebooks for Local Model Fine-Tuning and Inference (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes), Base vs fine-tuned Gemma 4 E2B as a model router (Melvin Vivas on X · notes) and 3 more
• GLiNER2.5-Decide · tool · huggingface.co · free
  A 340M-parameter open-weight encoder model that answers user-defined typed questions and rules for fast, deterministic classification.
  Also in: AIBackends v0.8.1 adds GLiNER2.5-Decide local classification (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes), GLiNER2.5-Decide: A 340M Encoder Model for Deterministic Classification (Melvin Vivas on X · notes)
• Fastino Labs (@fastinoAI) on X · person · x.com · free
  The X account of Fastino Labs, which builds GLiNER decision models and shares demos.
  Also in: GLiDE: Fastino's Decision Model with Adaptive Thinking (Melvin Vivas on X · notes), GLiDE by Fastino Labs: A Post-Trainable Reasoning Decision Model (Melvin Vivas on X · notes), GLiNER decision model demos from Fastino Labs (Melvin Vivas on X · notes), AIBackends v0.8.1 adds GLiNER2.5-Decide local classification (Melvin Vivas on X · notes) and 4 more
• Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Free GPU notebooks.
  Also in: Run Notebooks on a Free GPU with Google Colab (T4, 15GB VRAM) (Melvin Vivas on X · notes), Run Local Models on a Free GPU with Google Colab (T4) (Melvin Vivas on X · notes), Free Colab Notebooks for Local Model Fine-Tuning and Inference (Melvin Vivas on X · notes), Intent classification for support using GLiNER2.5-Decide notebook (Melvin Vivas on X · notes) and 12 more

Try this

• Download the GLiNER2.5-Decide notebook from donvito/notebooks and run the examples on CPU or GPU in Colab.
• Use GLiNER2.5-Decide to build a fast rule-based classifier from your own typed questions and rules.