Transformer

A library for finding knowledge neurons in pretrained transformer models

knowledge-neurons An open source repository replicating the 2021 paper Knowledge Neurons in Pretrained Transformers by Dai et al., and extending the technique to autoregressive models, as well as MLMs. The Huggingface Transformers library is used as the backend, so any model you want to probe must be implemented there. Currently integrated models: BERT_MODELS = [“bert-base-uncased”, “bert-base-multilingual-uncased”] GPT2_MODELS = [“gpt2”] GPT_NEO_MODELS = [ “EleutherAI/gpt-neo-125M”, “EleutherAI/gpt-neo-1.3B”, “EleutherAI/gpt-neo-2.7B”, ] The technique from Dai et al. has been used to locate knowledge neurons in […]

Read more
RESTful API

Boilerplate code for quick docker implementation of REST API

Boilerplate code for quick docker implementation of REST API with JWT Authentication using FastAPI, PostgreSQL and PgAdmin. Getting Started Features Auth Description Login Access Token OAuth2 compatible token login, get an access token for future requests Check Session Test if a user is logged in by checking if a valid access token is in the header Recover Password Password Recovery Reset Password Reset your password User Description Create New User Create a new user Get Current User By Id Get […]

Read more
Database

A Relational Database Management System for a miniature version of Twitter written in python

Mini-Twitter-Database This was done as a database design course project at Amirkabir university of technology. This is a relational database management system that is built using MySQL and works with CLI in python. This project contains the following files: tables.sql: A DDL script to generate relational tables for our mini-twitter schema including relevant constraints. procedures.sql: Several procedures to perform complex queries. triggers.sql: Some triggers that are sensitive to a particular event and perform specific tasks as they occur. Relational_schema.png: Relational […]

Read more
Dataset

A work-in-progress vector version of the MNIST dataset

bezier-mnist This is a work-in-progress vector version of the MNIST dataset. Here are some samples from the training set. Note that, while these are rasterized, the underlying images can be rendered at any resolution because they are smooth vector graphics. ![A grid of sixteen digit images](https://github.com/unixpickle/bezier-mnist/raw/main/samples.png =300×300) I have already converted all of MNIST to Bezier curves. This dataset can be downloaded at this page. There are two files: train.zip and test.zip, each containing a separate json file for each […]

Read more
Django

Pydantic models for Django

Djantic Documentation: https://jordaneremieff.github.io/djantic/ Requirements: Python 3.7+, Django 3.0+ Pydantic models for Django. This project should be considered a work-in-progress. It should be okay to use, but no specific version support has been determined (#16) and the default model generation behaviour may change across releases. Please use the issues tracker to report any bugs, or if something seems incorrect. Quickstart Install using pip: pip install djantic Generating schemas from models Configure a custom ModelSchema class for a Django model to generate […]

Read more
Asyncio

An Asynchronous Python object-document mapper for MongoDB

beanie Beanie – is an Asynchronous Python object-document mapper (ODM) for MongoDB, based on Motor and Pydantic. When using Beanie each database collection has a corresponding Document that is used to interact with that collection. In addition to retrieving data, Beanie allows you to add, update, or delete documents from the collection as well. Beanie saves you time by removing boiler-plate code and it helps you focus on the parts of your app that actually matter. Data and schema migrations […]

Read more
Voice

Unofficial PyTorch implementation of Google AI’s VoiceFilter system

Hi everyone! It’s Seung-won from MINDs Lab, Inc. It’s been a long time since I’ve released this open-source, and I didn’t expect this repository to grab such a great amount of attention for a long time. I would like to thank everyone for giving such attention, and also Mr. Quan Wang (the first author of the VoiceFilter paper) for referring this project in his paper. Actually, this project was done by me when it was only 3 months after I […]

Read more
Neural Network

A library for the Unbounded Interleaved-State Recurrent Neural Network algorithm

UIS-RNN This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization. This algorithm was originally proposed in the paperFully Supervised Speaker Diarization. The work has been introduced byGoogle AI Blog. Disclaimer This open source implementation is slightly different than the internal onewhich we used to produce the results in thepaper, due to dependencies onsome internal libraries. We CANNOT share the data, code, or model for the speaker recognition system(d-vector […]

Read more
Natural Language Processing

A sentence embeddings method that provides semantic representations

InferSent InferSent is a sentence embeddings method that provides semantic representations for English sentences. It is trained on natural language inference data and generalizes well to many different tasks. We provide our pre-trained English sentence encoder from our paper and our SentEval evaluation toolkit. Recent changes: Removed train_nli.py and only kept pretrained models for simplicity. Reason is I do not have time anymore to maintain the repo beyond simple scripts to get sentence embeddings. Dependencies This code is written in […]

Read more
BERT

Pytorch implementation of Google AI’s 2018 BERT with simple annotation

BERT-pytorch Pytorch implementation of Google AI’s 2018 BERT, with simple annotation BERT 2018 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Paper URL : https://arxiv.org/abs/1810.04805 Google AI’s BERT paper shows the amazing result on various NLP task (new 17 NLP tasks SOTA),including outperform the human F1 score on SQuAD v1.1 QA task.This paper proved that Transformer(self-attention) based encoder can be powerfully used asalternative of previous language model with proper language model training method.And more importantly, they showed us that […]

Read more
1 … 541 542 543 544 545 … 940