nlp-uoregon/Okapi

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

31
/ 100
Emerging

Okapi provides ready-to-use large language models (LLMs) and training data that understand and generate text in 26 different languages. It takes instructions and context in one of these languages and produces human-like text responses. This is for researchers and developers working on multilingual natural language processing applications.

No commits in the last 6 months.

Use this if you are a researcher focused on exploring, evaluating, or building LLMs that need to function effectively across a wide range of languages, including less common ones.

Not ideal if you need a solution for commercial use, as the provided models and datasets are restricted to research purposes only.

multilingual-AI language-model-research NLP-development AI-ethics-and-governance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

96

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Aug 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/nlp-uoregon/Okapi"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.