Pomilon/LEMA-llama
A Proof of Concept for the LEMA (Layer-wise Efficient Memory Abstraction) framework. Enables stable fine-tuning of Llama-2-7B on consumer-grade hardware (16GB VRAM) through layer-wise weight streaming and triple-buffer memory virtualization.
Stars
1
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Pomilon/LEMA-llama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
THU-ESIS/Chinese-Mistral
Chinese-Mistral: An Efficient and Effective Chinese Large Language Model
l294265421/my-alpaca
Reproduce alpaca
mps256/vicuna.ps1
This is a PowerShell script that automates the process of setting up and running VICUNA on a CPU...
Dannyj1/mistral-java-client
Mistral-java-client is a client for the Mistral.ai API. It allows you to easily interact with...
zygmuntz/AlpacaGPT
How to train your own ChatGPT, Alpaca style