affjljoo3581/polyglot-jax-inference

TPU에서 한국어용 LLM 추론을 위한 Jax/Flax 구현체입니다.

32
/ 100
Emerging

This project offers a way to run large language models (LLMs) specifically for the Korean language on Google's Tensor Processing Units (TPUs). It takes an existing Korean LLM, such as Polyglot-ko or KORani, and processes it to generate Korean text. This is designed for developers and researchers working with large-scale Korean natural language processing tasks who need high-performance inference.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher focused on deploying or experimenting with Korean language models based on the GPT-NeoX architecture for efficient text generation on TPUs.

Not ideal if you are looking to deploy LLaMA-based Korean models or if you do not have access to or experience with TPU environments and Jax/Flax.

Korean NLP LLM Inference Text Generation Deep Learning Deployment TPU Computing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

Python

License

MIT

Last pushed

Jun 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/affjljoo3581/polyglot-jax-inference"

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