OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

X Transformer

X Transformer is experimental research code for extreme multi-label text classification with pretrained transformers. Its documented workflow includes label indexing, model preparation, ranking and evaluation, with example procedures for benchmark datasets and custom data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

X Transformer — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when exploring or reproducing research workflows for assigning many possible labels to text, especially when you can provide the documented feature matrices, label assignments, raw text and label descriptions.

Who it is for

  • Researchers studying extreme multi-label text classification.
  • Developers prototyping large-label text tagging or categorization pipelines.
  • Practitioners comparing linear-model and fine-tuned-transformer evaluation workflows.

Documented uses

  • Prepare label embeddings and hierarchical label-to-cluster assignments.
  • Prepare custom text and label data for transformer models.
  • Train or predict with linear and fine-tuned transformer workflows and evaluate Precision/Recall@k.
  • Reproduce documented experiments on the listed benchmark datasets.
Before you choose

Requirements & limits

The repository is public and identifies the BSD-3-Clause license. The README provides a Conda-based setup sequence.

  • The repository labels its code experimental, while also pointing to PECOS as a newer implementation.
  • Custom-data preparation requires separate train/test feature matrices, instance-to-label matrices, raw text files and a label map.
  • The documented custom pipeline has three stages: Indexer, Matcher and Ranker.
  • The README supplies benchmark-data and pretrained-model download workflows, as well as separate linear and transformer evaluation scripts.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the project in its documented Conda environment

Set up the repository package using the README’s Conda and Python installation sequence.

Before you start

  • Repository checkout
  • Conda
  • The repository's environment.yml file

Steps

  1. Create the Conda environment with conda env create -f environment.yml.

  2. Activate it with source activate pt1.2_xmlc_transformer.

  3. Run pip install -e . in the activated environment.

  4. Run python setup.py install --force in the activated environment.

Expected outcome

The README's documented package installation sequence is complete in the named Conda environment.

Guide limitations

  • This setup sequence does not run a classification or evaluation workflow.
  • The README notes that its examples use the pt1.2_xmlc_transformer environment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
OctoberChang/X-Transformer · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

PECOS — The X Transformer README points to PECOS as the location of a newer implementation, described there as faster with stronger performance.

Explore project →