SensAI-PT/LLaMa2lang

Convenience scripts to finetune (chat-)LLaMa3 and other models for any language

42
/ 100
Emerging

This project helps you take powerful large language models (like LLaMa3) that are mostly trained in English and adapt them to understand and generate text fluently in other languages. You provide an existing English instruction dataset, and the tool translates it and fine-tunes the language model. The result is a specialized chatbot or AI that performs much better in your desired non-English language than generic models. It's ideal for AI developers or researchers creating localized AI applications.

313 stars. No commits in the last 6 months.

Use this if you need an AI model like LLaMa3 to perform conversations and follow instructions effectively in a specific language other than English.

Not ideal if your primary need is for an English-only model or if you prefer a pre-trained model without any custom language adaptation.

natural-language-processing localization chatbot-development multilingual-ai instruction-following-models
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

313

Forks

34

Language

Python

License

Apache-2.0

Category

llm-fine-tuning

Last pushed

Jun 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SensAI-PT/LLaMa2lang"

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