Hey Welcome back! Want to start off by giving a few shout outs!!!
- Hectiq.AI hosted the big-yaml — Neural Magic’s config to serve 19 BERT models simultaneously, all under 16GBs of RAM! 😍 Demo
- If you want to know more about the demo above, you can read about it here: Thank you KDnuggets and Towards AI! 🚀
- Scrape tweets with Twint and classify it with a Neural Magic Sparse Transformer: Code 🧙♂️
Stanford AI Lab Papers and Talks at ICLR 2022
The International Conference on Learning Representations (ICLR) 2022 is being hosted virtually from April 25th - April…
Google at ICLR 2022
The 10th International Conference on Learning Representations ( ICLR 2022) kicks off this week, bringing together…
Featured Event LatinX in AI will host a virtual social co-located with the International Conference on Learning…
The International Conference on Learning Representations is the premier gathering of academic and industrial…
Apple is sponsoring the International Conference on Learning Representations (ICLR). It will be held virtually from…
DeepMind's latest research at ICLR 2022
Today, conference season is kicking off with The Tenth International Conference on Learning Representations ( ICLR…
FormNet: A New Model for Document Understanding
FormNet: Beyond Sequential Modeling for Form-Based Document Understanding
Form-based document understanding is a growing research topic because of its practical potential for automatically…
WaNLI: Generate Your Own NLI dataset
Run Python in the Browser via HTML
The makers of Anaconda came out with this. 🍾❤️
Has only been tested on Chrome thus far.
Anaconda | New from Anaconda: Python in the Browser
pyscript.net Supporting open source and creating tools that enable people to do more with less are why I joined…
PyScript is a framework that allows users to create rich Python applications in the browser using HTML's interface…
GitHub - pyscript/pyscript
PyScript is a Pythonic alternative to Scratch, JSFiddle or other "easy to use" programming frameworks, making the web a…
DALL-E-2 | Performance and Limitations
Limitations of DALL-E-2 | a thread 🧵
DALL-E-2 PyTorch Implementation
Lucidrains for the win!
GitHub - lucidrains/DALLE2-pytorch: Implementation of DALL-E 2, OpenAI's updated text-to-image…
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch. Yannic Kilcher summary…
SEAL 🦭 Search Engines w/ Autoregressive LMs
Thread by @MicheleBevila20 on Thread Reader App
New work on autoregressive language models for retrieval! We train our model, SEAL (Search Engines with Autoregressive…
GitHub - facebookresearch/SEAL: Search Engines with Autoregressive Language models
This repo hosts the code for our paper, SEAL. https://arxiv.org/abs/2204.10628 We propose a approach to retrieval that…
GitHub - labmlai/neox: Simple Annotated implementation of GPT-NeoX in PyTorch
Simple Annotated implementation of GPT-NeoX in PyTorch - GitHub - labmlai/neox: Simple Annotated implementation of…
DiffCSE — Meta’s New Sentence Embeddings Library
GitHub - voidism/DiffCSE: Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive…
arXiv link: https://arxiv.org/abs/2204.10298 To be published inNAACL 2022 Authors: Yung-Sung Chuang, Rumen Dangovski…
OpenAIs New Clip Model
(a silent drop)
ViT-L/14@336px (#234) · openai/CLIP@b4ae449
You can't perform that action at this time. You signed in with another tab or window. You signed out in another tab or…
Stoic Quotes | The best quotes from the great Roman Stoics
The very best Stoic quotes from the three great Roman Stoics: Marcus Aurelius, Seneca, and Epictetus. Presented in…
Papers to Read 📚
A collection of recently released repos that caught our 👁
An open-source online generative dictionary that takes a word and context containing the word as input and automatically generates a definition as output.
GitHub - blcuicall/litmind-dictionary
LitMind Dictionary( https://dictionary.litmind.ink) is an open-source online generative dictionary that takes a word…
A novel skill extraction dataset consisting of 14.5K sentences and over 12.5K annotated spans from job postings.
GitHub - kris927b/SkillSpan: SKILLSPAN: Competences as Spans for Skill Extraction from Job Postings
This repository contains the code and data for the paper: SkillSpan: Hard and Soft Skill Extraction from Job Postings…
jjzha (Mike Zhang)
We're on a journey to advance and democratize artificial intelligence through open source and open science.
An interactive debugger tool for transformer-based LMs, which provides a fine-grained interpretation of the model’s internal prediction process.
GitHub - mega002/lm-debugger: The official code of LM-Debugger, an interactive tool for inspection…
LM-Debugger is an open-source interactive tool for inspection and intervention in transformer-based language models…
The first large-scale dataset of dialogues transitioning from chit-chat to task-oriented scenarios.
GitHub - MiuLab/SalesBot: Transitioning from Open-Domain Chit-Chat to Task-Oriented Dialogues
Transitioning from Open-Domain Chit-Chat to Task-Oriented Dialogues - GitHub - MiuLab/SalesBot: Transitioning from…
An abbreviation detection dataset for scientific documents.
GitHub - surrey-nlp/PLOD-AbbreviationDetection: This repository contains the PLOD Dataset for…
This is the repository for PLOD Dataset submitted to LREC 2022. The dataset can help build sequence labelling models…