somosnlp-hackathon-2026

Onexe

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: mit

What is Onexe

Onexe is a research prototype designed to:

  • generate responses in Spanish with a Canary Islands style
  • incorporate Canary vocabulary, expressions, and cultural references
  • use curated knowledge sources to improve factual and cultural answers

Official repository

You can find the full codebase, documentation, and development progress on GitHub:

https://github.com/siani-big-data/2026-HackathonSomosNLP

Project approach

The system is built around two main components:

  • Conversational post-training to teach the model to respond in a more natural Canary Islands Spanish style
  • Optional RAG to retrieve context from curated cultural and lexical sources before generating an answer

Status

Onexe is currently a research prototype.

Authors

  • Óscar Rico Rodríguez
  • Ricardo Cárdenes
  • José Juan Hernández Gálvez

License

MIT

Model provider

somosnlp-hackathon-2026

Model tree

Base

Qwen/Qwen2.5-7B-Instruct

Adapter

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today