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/transformers/Pomilon/LEMA-llama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mistralai/mistral-inference
Official inference library for Mistral models
dvmazur/mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
open-compass/MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
vicuna-tools/vicuna-installation-guide
The "vicuna-installation-guide" provides step-by-step instructions for installing and...
pleisto/yuren-13b
Yuren 13B is an information synthesis large language model that has been continuously trained...