OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Ask2Transformers

Ask2Transformers is an open-source Python framework that uses textual entailment models for zero-shot text classification, including topic labelling, relation extraction and event argument extraction. It builds on Hugging Face Transformers and PyTorch, and lets developers select compatible models or define classifiers with label descriptions and templates.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ask2Transformers — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a text-processing project needs zero-shot classification or extraction configured through labels and templates, and the chosen model is compatible with the Transformers sequence-classification interface.

Who it is for

  • Python developers building text-classification or information-extraction workflows
  • Researchers reproducing or adapting entailment-based classification experiments

Documented uses

  • Assign topics to text using a configurable label set.
  • Extract relations using verbalized labels or templates.
  • Reuse task-specific pretrained entailment models with new schemas for the same tasks.
  • Prepare task data as natural-language-inference data for custom model training.
Before you choose

Requirements & limits

The project is publicly available under the Apache-2.0 license.

  • The default inference checkpoint is roberta-large-mnli; other listed models include XLM-RoBERTa XNLI, BART MNLI and DeBERTa-v2 XLarge MNLI.
  • Selectable models must be fine-tuned on a natural language inference task and compatible with Transformers AutoModelForSequenceClassification.
  • Some pretrained models expect bracket-marked input spans, so their training preprocessing needs to be matched.
  • The repository describes custom training through NLI-format data and an example conversion script, rather than a dedicated fine-tuning script.

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 Ask2Transformers from the repository

Install the Python package from a local clone of its GitHub repository.

Before you start

  • Python package installation environment
  • Git

Steps

  1. Clone https://github.com/osainz59/Ask2Transformers.git.

  2. Change into the Ask2Transformers directory.

  3. Run pip install .

Expected outcome

The package is installed from the cloned repository.

Guide limitations

  • This installation recipe does not configure a model or run a classifier.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Ask2TransformersAssign topics to text using a configurable label set.The project is publicly available under the Apache-2.0 license.
HyperposeCustomize pose-estimation architectures and datasets.Docker, Linux, macOS, Windows
Multi Task NlpDefine multiple tasks and their data and model settings in a YAML file.Linux, macOS, WindowsThe project is an open-source library under the Apache-2.0 license, distributed through its public GitHub repository.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
osainz59/Ask2Transformers · Official homepage title · retained in its source language
How we review sourcesSuggest a correction