adithya-s-k/Indic-llm

A open-source framework designed to adapt pre-trained Language Models (LLMs), such as Llama, Mistral, and Mixtral, to a wide array of domains and languages.

26
/ 100
Experimental

This project helps bridge the language gap for large language models (LLMs), allowing them to understand and generate content in Kannada, a language often underrepresented in existing models. It takes pre-trained LLMs and adapts them, using a blend of Kannada and English text, to produce a model capable of interacting effectively in both languages. This is ideal for researchers, businesses, or content creators who need LLMs to serve Kannada-speaking audiences or process Kannada text.

No commits in the last 6 months.

Use this if you need a large language model that can effectively process and generate content in both Kannada and English, especially when working with limited Kannada data.

Not ideal if your primary need is for a monolingual English LLM or if you require support for a language other than Kannada or English.

natural-language-processing bilingual-content language-localization AI-research multilingual-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

23

Forks

1

Language

Python

License

GPL-3.0

Category

llm-fine-tuning

Last pushed

May 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/adithya-s-k/Indic-llm"

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