bert-distillation
by elephantmipt
Distillation of BERT model with catalyst framework
AI summary
BERT distiller
A high-level API for distilling BERT models to create smaller, more efficient variants with reduced training time and improved inference speed.
- stars
- 75
- forks
- 7
- watching
- 4
Similar projects
Found by comparing what the projects do, not just their names.
Knowledge Distiller
A Python-based project implementing contrastive representation distillation and benchmarking recent knowledge distillation methods
Model distiller
Automatically trains models from large foundation models to perform specific tasks with minimal human intervention.
dbmdz/berts155
NLP library
Provides pre-trained language models for natural language processing tasks
Poetry model
A BERT-based pre-trained model for Chinese classical poetry
Word-based Chinese Model
A Word-based Chinese BERT model trained on large-scale text data using pre-trained models as a foundation
Language model library
Provides pre-trained language models derived from Wikipedia texts for natural language processing tasks
Experiment builder
A framework for designing and running deep learning experiments without writing code
Federated Learning Framework
An implementation of a heterogenous federated learning framework using model distillation.
Data Sorter
Automated sorting of data using a neural network model
NLP libraries
Pre-trained language models for biomedical natural language processing tasks
BERT NER
An implementation of named entity recognition using Google's BERT model for the CoNLL-2003 dataset and Python.
mop/bier39
Metric learner
This project implements a deep metric learning framework using an adversarial auxiliary loss to improve robustness.
Distributed Backpropagation Library
Enables backpropagation in distributed settings and facilitates model parallelism using differentiable communication between processes
NLP transformer model
Implementing BERT-like NLP models in OCaml using PyTorch bindings and pre-trained weights from popular sources.
Diffusion toolkit
A toolkit for creating and manipulating state-of-the-art diffusion models in PyTorch
