Mxbonn/ltmp
Code for Learned Thresholds Token Merging and Pruning for Vision Transformers (LTMP). A technique to reduce the size of Vision Transformers to any desired size with minimal loss of accuracy.
This project helps machine learning engineers and researchers optimize Vision Transformers for practical deployment. It takes an existing Vision Transformer model and outputs a smaller, more computationally efficient version with minimal impact on accuracy. This is ideal for those developing and deploying computer vision applications where performance and resource usage are critical.
No commits in the last 6 months.
Use this if you need to reduce the computational cost and size of your Vision Transformer models for deployment, especially in resource-constrained environments.
Not ideal if your primary concern is developing novel Vision Transformer architectures rather than optimizing existing ones.
Stars
17
Forks
1
Language
Python
License
—
Category
Last pushed
Nov 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Mxbonn/ltmp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Goekdeniz-Guelmez/mlx-lm-lora
Train Large Language Models on MLX.
uber-research/PPLM
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
VHellendoorn/Code-LMs
Guide to using pre-trained large language models of source code
ssbuild/chatglm_finetuning
chatglm 6b finetuning and alpaca finetuning
jarobyte91/pytorch_beam_search
A lightweight implementation of Beam Search for sequence models in PyTorch.