serp-ai/LLaMA-8bit-LoRA

Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.

31
/ 100
Emerging

This project helps AI researchers and machine learning engineers adapt large language models (LLMs) like LLaMA to specific tasks or datasets using limited computational resources. It takes a base LLaMA model and your specialized dataset, then outputs a smaller, fine-tuned model (LoRA adapter) that's more efficient to run and deploy. This is for those looking to customize LLMs without needing extensive GPU power.

150 stars. No commits in the last 6 months.

Use this if you are an AI researcher or ML engineer who needs to fine-tune LLaMA models on custom data using less memory and faster training times.

Not ideal if you are an end-user simply looking to chat with or use a pre-trained LLaMA model out-of-the-box for general purposes.

AI-research LLM-customization model-fine-tuning resource-optimization machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

150

Forks

15

Language

Python

License

Category

llm-fine-tuning

Last pushed

Aug 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/serp-ai/LLaMA-8bit-LoRA"

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