teticio/llama-squad

Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.

40
/ 100
Emerging

This project helps machine learning engineers and researchers adapt large, generalized AI models (like Llama 2 or 3) to perform very specific question-answering tasks. It takes a foundation model and a dataset of questions, contexts, and exact answers, then outputs a specialized model that can accurately extract answers or state when an answer isn't present. It's for those looking to fine-tune existing large language models for precise information extraction.

No commits in the last 6 months.

Use this if you need to train a large language model to precisely extract answers from provided text and 'know' when the answer is not available.

Not ideal if you're looking for a general-purpose chatbot or a model that generates creative, open-ended responses.

Machine Learning Engineering Natural Language Processing Information Extraction Model Specialization Question Answering Systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

53

Forks

10

Language

Python

License

GPL-3.0

Last pushed

Jun 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/teticio/llama-squad"

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