mlsw/partial-embedding-matrix-adaptation
Vocabulary-level memory efficiency for language model fine-tuning.
This tool helps machine learning engineers and researchers fine-tune large language models more efficiently. It takes an existing pre-trained language model and your specific dataset, then outputs a fine-tuned model with a significantly reduced memory footprint, without sacrificing performance. This is for professionals working with deep learning and natural language processing.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher fine-tuning a language model and are encountering memory limitations on your hardware.
Not ideal if you are not working with language models or are not concerned with memory usage during fine-tuning.
Stars
8
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mlsw/partial-embedding-matrix-adaptation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
adapter-hub/adapters
A Unified Library for Parameter-Efficient and Modular Transfer Learning
gaussalgo/adaptor
ACL 2022: Adaptor: a library to easily adapt a language model to your own task, domain, or...
ylsung/VL_adapter
PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language...
intersun/LightningDOT
source code and pre-trained/fine-tuned checkpoint for NAACL 2021 paper LightningDOT
kyegomez/M2PT
Implementation of M2PT in PyTorch from the paper: "Multimodal Pathway: Improve Transformers with...