-
Introducing GPTs
https://openai.com/blog/introducing-gpts?fbclid=IwAR1bc_tWeq8ejhleFn2qn-pPjY7Ch5tvWCvG1skwMrI_kNaUk4cgek4dcl0
-
mlfoundations/open_clip: An open source implementation of CLIP.
https://github.com/mlfoundations/open_clip
-
Getting the most from cloud services and containers | McKinsey
https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/getting-the-most-from-cloud-services-and-containers?cid=soc-app&utm_content=buffer1e14a&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
Docker Images,Docker file and port expose
https://medium.com/@aakib2991/docker-part-3-docker-images-docker-file-and-port-expose-885d57d2e697
-
A psychometric assessment on Emotional Intelligence of Large Language Models
https://emotional-intelligence.github.io/?fbclid=IwAR0PggfJG_554P0PIECzj26xYKSvG0x_ttTMYwwUAZKIB0C3OTqcRcvNC2g
-
2 October, 2023 07:47
https://generativeai.pub/graph-of-thoughts-explained-f25b51afefab?gi=df0413646530
-
Knowledge Graphs & LLMs: Real-Time Graph Analytics | by Tomaz Bratanic | Neo4j Developer Blog | Jul, 2023 | Medium
https://medium.com/neo4j/knowledge-graphs-llms-real-time-graph-analytics-89b392eaaa95
-
LangChain 🤝 Streamlit
https://blog-streamlit-io.cdn.ampproject.org/c/s/blog.streamlit.io/langchain-streamlit/amp/
-
JourneyDB/JourneyDB · Datasets at Hugging Face
https://huggingface.co/datasets/JourneyDB/JourneyDB
-
Transformers.js
https://huggingface.co/docs/transformers.js/index
-
How I Coded My Own Private French Tutor Out of ChatGPT | by Shaked Zychlinski | Jun, 2023 | Towards Data Science
https://towardsdatascience.com/how-i-coded-my-own-private-french-tutor-out-of-chatgpt-16b3e15007bb
-
Tracking Everything Everywhere All at Once
https://omnimotion.github.io/
-
GitHub – NielsRogge/Transformers-Tutorials: This repository contains demos I made with the Transformers library by HuggingFace.
https://github.com/NielsRogge/Transformers-Tutorials
-
GitHub – XingangPan/DragGAN: Official Code for DragGAN (SIGGRAPH 2023)
https://github.com/XingangPan/DragGAN
-
2306.07629 SqueezeLLM: Dense-and-Sparse Quantization
https://arxiv.org/abs/2306.07629
-
What runs ChatGPT? Inside Microsoft’s AI supercomputer | Featuring Mark Russinovich
https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/what-runs-chatgpt-inside-microsoft-s-ai-supercomputer-featuring/ba-p/3830281?utm_content=buffer3d7e2&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
LaMini is here: a little giant LLM on your CPU
https://artificialcorner.com/lamini-is-here-a-little-giant-llm-on-your-cpu-8af30ff5a7c2?gi=263024e685a2
-
Transformer models: an introduction and catalog — 2023 Edition – AI, software, tech , and people, not in that order… by X
https://amatriain.net/blog/transformer-models-an-introduction-and-catalog-2d1e9039f376/
-
A Simple Tool to Start Making Decisions with the Help of AI
https://hbr.org/2018/04/a-simple-tool-to-start-making-decisions-with-the-help-of-ai
-
2304.12210 A Cookbook of Self-Supervised Learning
https://arxiv.org/abs/2304.12210
-
GitHub – h2oai/h2ogpt: Come join the movement to make the world’s best open source GPT led by H2O.ai
https://github.com/h2oai/h2ogpt
-
Microsoft Open-Sources Multimodal Chatbot Visual ChatGPT
https://www.infoq.com/news/2023/04/microsoft-visual-chatgpt/?utm_term=global&utm_content=buffer1c1e8&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
HuggingGPT – a Hugging Face Space by microsoft
https://huggingface.co/spaces/microsoft/HuggingGPT
-
GitHub – jina-ai/gptdeploy: One line to create them all
https://github.com/jina-ai/gptdeploy
-
The Complete Guide to Spiking Neural Networks | by Ali Moezzi | Apr, 2023 | Towards AI
https://pub.towardsai.net/the-complete-guide-to-spiking-neural-networks-d0a85fa6a64
-
What is PL/Rust? – PL/Rust Guide
https://tcdi.github.io/plrust/plrust.html
-
GitHub – mrsked/mrsk: Deploy web apps anywhere.
https://github.com/mrsked/mrsk
-
PCA for Multivariate Time Series: Forecasting Dynamic High-Dimensional Data
System Forecasting in Presence of Noise and Serial Correlation https://towardsdatascience.com/pca-for-multivariate-time-series-forecasting-dynamic-high-dimensional-data-ab050a19e8db
-
Four Approaches to build on top of Generative AI Foundational Models
https://towardsdatascience.com/four-approaches-to-build-on-top-of-generative-ai-foundational-models-43c1a64cffd5 Four Approaches to build on top of Generative AI Foundational Models What works, the pros and cons, and example code for each approach towardsdatascience.com
-
2212.02691 LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training
https://arxiv.org/abs/2212.02691
-
Alpaca – Stanford CRFM
https://crfm.stanford.edu/2023/03/13/alpaca.html
-
GitHub – GoogleContainerTools/distroless: 🥑 Language focused docker images, minus th e operating system.
https://github.com/GoogleContainerTools/distroless
-
Could you train a ChatGPT-beating model for $85,000 and run it in a browser?
https://simonwillison.net/2023/Mar/17/beat-chatgpt-in-a-browser/
-
Export to ONNX – a Hugging Face Space by onnx
https://huggingface.co/spaces/onnx/export
-
6 New Booming Data Science Libraries You Must Learn To Boost Your Skill Set in 2023
Data science isn’t just Pandas, NumPy, and Scikit-learn anymore https://towardsdatascience.com/6-new-booming-data-science-libraries-you-must-learn-to-boost-your-skill-set-in-2023-106b318d9fa
-
ELSAR 2022 – Sort benchmark
http://sortbenchmark.org/ELSAR2022.pdf
-
Developer Resources from Intel & Hugging Face
https://www.intel.com/content/www/us/en/developer/partner/hugging-face.html
-
GitHub – szheng3/rust-individual-project-2: Rust server that summarizes text with pre-trained models
https://github.com/szheng3/rust-individual-project-2
-
amazon-science/mm-cot: Official implementation for « Multimodal Chain-of-Thought Reasoning in Language Models » (stay tuned and more will be updated)
https://github.com/amazon-science/mm-cot
-
20 February, 2023 21:29
https://github.com/nogibjj/rust-mlops-template/tree/static/OnnxDemo
-
Graph Neural Networks Go Forward-Forward
Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph’s nodes. This allows training graph neural networks with forward passes only, without backpropagation. https://arxiv.org/abs/2302.05282 Graph Neural Networks Go Forward-Forward We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able…
-
Pix2Pix Video – a Hugging Face Space by fffiloni
https://huggingface.co/spaces/fffiloni/Pix2Pix-Video
-
Sustainability with Rust | AWS Open Source Blog
https://aws.amazon.com/fr/blogs/opensource/sustainability-with-rust/
-
GokuMohandas/Made-With-ML: Learn how to responsibly develop, deploy and maintain production machine learning applications.
https://github.com/GokuMohandas/Made-With-ML
-
31 January, 2023 13:09
https://moez-62905.medium.com/decorating-your-python-code-a-beginners-guide-to-decorators-3bedb022cfe7
-
GitHub – databricks/mlops-stack
https://github.com/databricks/mlops-stack
-
GitHub – cookiecutter/cookiecutter: A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.
https://github.com/cookiecutter/cookiecutter
-
BART Text Summarization vs. GPT-3 vs. BERT: An In-Depth Comparison
https://www.width.ai/post/bart-text-summarization BART Text Summarization vs. GPT-3 vs. BERT: An In-Depth Comparison BART does a good job of producing a grammatically correct summary that covers both the focus areas — health and personality. It also removes all the spurious, unreadable text (like "@CAPS2"). www.width.ai
-
GitHub – dair-ai/ML-Papers-Explained: Explanation to key concepts in ML
https://github.com/dair-ai/ML-Papers-Explained
-
30 December, 2022 19:56
https://towardsdatascience.com/adam-latest-trends-in-deep-learning-optimization-6be9a291375c
-
A summary of Few-Shot Learning with Graph Neural Networks | by Nivedita Majee | Medium
https://medium.com/@dita.niki03/a-summary-of-few-shot-learning-with-graph-neural-networks-c33b5d0d7a6f
-
Deep Learning Is Not Just Inadequate for Solving AGI, It Is Useless | by Rebel Science | Nov, 2022 | Medium
https://medium.com/@RebelScience/deep-learning-is-not-just-inadequate-for-solving-agi-it-is-useless-2da6523ab107
-
Cramming: Training a Language Model on a Single GPU in One Day – Jonas Geiping and Tom Goldstein University of Maryland 2022
This repository contains code to replicate our research described in "Cramming: Training a Language Model on a Single GPU in One Day". We experiment with language model pretraining a BERT-type model with limited compute, wondering "how bad can it really be"? https://github.com/JonasGeiping/cramming GitHub – JonasGeiping/cramming: Cramming the training of a (BERT-type) language model into limited…
-
29 December, 2022 12:31
https://blog.qooba.net/2022/10/25/speedup-mlflow-models-serving-with-rust/
-
GitHub – Aeternalis-Ingenium/FastAPI-Backend-Template: A backend project template with FastAPI, PostgreSQL with asynchronous SQLAlchemy 2.0, Alembic for asynchronous database migration, and Docker.
https://github.com/Aeternalis-Ingenium/FastAPI-Backend-Template
-
AI learns to write computer code in ‘stunning’ advance
DeepMind’s AlphaCode outperforms many human programmers in tricky software challenges https://www.science.org/content/article/ai-learns-write-computer-code-stunning-advance AI learns to write computer code in ‘stunning’ advance Software runs the world. It controls smartphones, nuclear weapons, and car engines. But there’s a global shortage of programmers. Wouldn’t it be nice if anyone could explain what they want a program to do, and…
-
Top Python libraries of 2022 you should know about | Tryolabs
Welcome to the 8th edition of our Top Python Libraries list! We are excited to present this year’s picks for the most innovative developments in the Python ecosystem. From this edition, we are expanding our list to include not only libraries per-se, but also tools that are built to belong in the Python ecosystem —…
-
Quantum Artificial Intelligence in Financial Crime | by Danny Butvinik | Analytics Vidhya | Medium
https://medium.com/analytics-vidhya/quantum-artificial-intelligence-in-financial-crime-24a6671915e7
-
20 December, 2022 09:51
A quick overview of ChatGPT’s architecture… The AI Powering ChatGPT: A clever combination of the InstructGPT architecture with reinforcement learning models. "The main ideas behind ChatGPT were pioneered by another OpenAI’s , InstructGPT which was released earlier this year. InstructGPT fine tunes GPT to follow instructions which opens the door to a wider set of…
-
How I Used ChatGPT To Automate These 6 Tasks In My Data Science Role | by Ahmed Besbes | Dec, 2022 | Level Up Coding
ChatGPT is like Google, StackOverflow and Readthedocs combined https://levelup.gitconnected.com/how-i-used-chatgpt-to-automate-these-6-tasks-in-my-data-science-role-52e8ddfc03cf
-
Training One Million Machine Learning Models in Record Time with Ray | Anyscale
https://www.anyscale.com/blog/training-one-million-machine-learning-models-in-record-time-with-ray
-
How we divided our server latency by 3 by switching from T4 GPUs to A10g | PhotoRoom Tech Blog
https://www.photoroom.com/tech/switching-from-t4-to-a10/
-
FastAPI for Machine Learning: Live coding an ML web application. – YouTube
https://m.youtube.com/watch?v=_BZGtifh_gw&feature=youtu.be
-
Meta AI Releases Data2vec 2.0: An Efficient Self-Supervised Learning For Machine Learning Tasks
Meta AI recently introduced Data2vec 2.0, an AI processor that uses computer vision for multi-camera multi-person re-identification. Data2vec 2.0 is 16 times faster than the current leading self-supervised method in computer vision and is just as accurate. It is 11 times faster than wav2vec 2.0 on the LibriSpeech benchmark and just as accurate as RoBERTa…
-
Illustrating Reinforcement Learning from Human Feedback (RLHF)
https://huggingface.co/blog/rlhf
-
Using an Out-of-Core Approach to Process Large Datasets
Faster big-data analysis workflows with an open-source library https://towardsdatascience.com/how-to-speed-up-data-processing-in-pandas-a272d3485b24
-
Should You Be Using Webhooks?. Introduction | by Fikayo Adepoju | Hookdeck | Medium
One of the simplest ways online applications share data is through the use of webhooks, a one-way communication format for moving data from one application to another. However, webhooks aren’t the only method for data transfer between networked applications. As an engineer, it is very important to use the right tool for the right problem,…
-
Stable Diffusion with Core ML on Apple Silicon – Apple Machine Learning Research
https://machinelearning.apple.com/research/stable-diffusion-coreml-apple-silicon
-
Google Dataset Search
https://datasetsearch.research.google.com/
-
Using MLOps to Build a Real-time End-to-End Machine Learning Pipeline | Binance Blog
https://www.binance.com/en/blog/all/using-mlops-to-build-a-realtime-endtoend-machine-learning-pipeline-3820048062346322706
-
CICERO: An AI agent that negotiates, persuades, and cooperates with people
Games have long been a proving ground for new AI advancements — from Deep Blue’s victory over chess grandmaster Garry Kasparov, to AlphaGo’s mastery of Go, to Pluribus out-bluffing the best humans in poker. But truly useful, versatile agents will need to go beyond just moving pieces on a board. Can we build more effective…
-
Magic3D: High-Resolution Text-to-3D Content Creation
Magic3D is a new text-to-3D content creation tool that creates 3D mesh models with unprecedented quality. Together with image conditioning techniques as well as prompt-based editing approach, we provide users with new ways to control 3D synthesis, opening up new avenues to various creative applications. https://deepimagination.cc/Magic3D/
-
Text Based Inpainting – a Hugging Face Space by nielsr
Demo for using CLIPSeg, a CLIP-based model for zero- and one-shot image segmentation. This model can be used to segment things in an image based on text. This way, one can use it to provide a binary mask for Stable Diffusion, which the latter needs to inpaint. To use it, simply upload an image and…
-
A visual guide on troubleshooting Kubernetes deployments
https://learnk8s.io/troubleshooting-deployments
-
Comprehensive Python Cheatsheet
https://gto76.github.io/python-cheatsheet/
-
2209.00099 Efficient Methods for Natural Language Processing: A Survey
Getting the most out of limited resources allows advances in natural language processing (NLP) research and practice while being conservative with resources. Those resources may be data, time, storage, or energy. Recent work in NLP has yielded interesting results from scaling; however, using only scale to improve results means that resource consumption also scales. That…
-
19 November, 2022 02:00
Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense. https://www-technologyreview-com.cdn.ampproject.org/c/s/www.technologyreview.com/2022/11/18/1063487/meta-large-language-model-ai-only-survived-three-days-gpt-3-science/amp/
-
Introducing more ways to deploy Azure Container Apps – Microsoft Community Hub
Azure Container Apps is a fully managed serverless container service for building and deploying modern apps at scale. Today, we’re introducing new preview features to make it even easier to build and deploy container apps: A new GitHub action to build and deploy container apps A new Azure Pipelines task to build and deploy container…
-
A Brain-Inspired Chip Can Run AI With Far Less Energy | Quanta Magazine
An energy-efficient chip called NeuRRAM fixes an old design flaw to run large-scale AI algorithms on smaller devices, reaching the same accuracy as wasteful digital computers. https://www.quantamagazine.org/a-brain-inspired-chip-can-run-ai-with-far-less-energy-20221110/
-
GitHub – paperswithcode/galai: Model API for GALACTICA
GALACTICA is a general-purpose scientific language model. It is trained on a large corpus of scientific text and data. It can perform scientific NLP tasks at a high level, as well as tasks such as citation prediction, mathematical reasoning, molecular property prediction and protein annotation. A demo is available at galactica.org. https://github.com/paperswithcode/galai
-
Which Feature Engineering Techniques improve Machine Learning Predictions?
Understanding the various feature engineering techniques can be handy for an ML practitioner. After all, features are one of the most determining factors about how machine learning and deep learning models perform in real-time. https://towardsdatascience.com/which-feature-engineering-techniques-improve-machine-learning-predictions-227d732068f5 Which Feature Engineering Techniques improve Machine Learning Predictions? | by Suhas Maddali | Nov, 2022 | Towards Data Science Photo…
-
Top Python libraries for Time Series Analysis in 2022
Python libraries and frameworks data scientists must know for time series analysis in 2022 https://moez-62905.medium.com/top-python-libraries-for-time-series-analysis-in-2022-eebe95913085
-
WIDeText: A Multimodal Deep Learning Framework | by Wayne Zhang | The Airbnb Tech Blog | Medium
How we designed a multimodal deep learning framework for quick product development, and how the Room Type Classification models built upon it helped us better understand the homes on our platform. https://medium.com/airbnb-engineering/widetext-a-multimodal-deep-learning-framework-31ce2565880c
-
14 November, 2022 04:48
The field of data science is always getting better, both in terms of the tools that are already available and those that are being developed every day. Even though no tool is flawless and comprehensive, having the right tools on your side can make a big difference in productivity and execution. https://moez-62905.medium.com/data-scientists-starter-toolkit-for-end-to-end-machine-learning-life-cycle-in-2022-2d2420bda22c
-
How I learn machine learning | Vicki Boykis
https://vickiboykis.com/2022/11/10/how-i-learn-machine-learning/
-
GitHub – visenger/awesome-mlops: A curated list of references for MLOps
An awesome list of references for MLOps – Machine Learning Operations https://github.com/visenger/awesome-mlops
-
8 November, 2022 23:05
https://karpathy.medium.com/software-2-0-a64152b37c35
-
MLflow and Azure Machine Learning – Azure Machine Learning | Microsoft Learn
MLflow is an open-source framework that’s designed to manage the complete machine learning lifecycle. Its ability to train and serve models on different platforms allows you to use a consistent set of tools regardless of where your experiments are running: locally on your computer, on a remote compute target, on a virtual machine, or on…
-
7 November, 2022 07:53
Learn the foundations of machine learning through intuitive explanations, clean code and visualizations. Learn how to combine machine learning with software engineering to build production-grade applications. https://github.com/GokuMohandas/Made-With-ML GokuMohandas/Made-With-ML: Learn how to responsibly develop, deploy and maintain production machine learning applications. – GitHub Mission. ML is not a separate industry, instead, it’s a powerful way of…
-
2209.07663 Monolith: Real Time Recommendation System With Collisionless Embedding Table (Tik Tok)
Building a scalable and real-time recommendation system is vital for many businesses driven by time-sensitive customer feedback, such as short-videos ranking or online ads. Despite the ubiquitous adoption of production-scale deep learning frameworks like TensorFlow or PyTorch, these general-purpose frameworks fall short of business demands in recommendation scenarios for various reasons: on one hand, tweaking…
-
6 November, 2022 20:33
Reinforcement learning (RL) is an area of machine learning that focuses on training intelligent agents using related experiences so they can learn to solve decision making tasks, such as playing video games, flying stratospheric balloons, and designing hardware chips. Due to the generality of RL, the prevalent trend in RL research is to develop agents…
-
Language Models are Realistic Tabular Data Generators
Tabular data is among the oldest and most ubiquitous forms of data. However, the generation of synthetic samples with the original data’s characteristics still remains a significant challenge for tabular data. While many generative models from the computer vision domain, such as autoencoders or generative adversarial networks, have been adapted for tabular data generation, less…
-
Code-to-cloud with Azure Kubernetes Service (AKS)
https://techcommunity.microsoft.com/t5/apps-on-azure-blog/code-to-cloud-with-azure-kubernetes-service-aks/ba-p/3669916?utm_content=buffere4c0d&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
Make a video content analyzer app with Streamlit and AssemblyAI
https://blog.streamlit.io/make-a-video-content-analyzer-app-with-streamlit-and-assemblyai/
-
9 Docker Extensions Every Developer Must Try
https://dev.to/docker/9-docker-extensions-every-developer-must-try-1no2
-
Search PDFs with AI and Python
With neural search seeing rapid adoption, more people are looking at using it for indexing and searching through their unstructured data. I know several folks already building PDF search engines powered by AI, so I figured I’d give it a stab too. How hard could it possibly be? https://jina.ai/news/search-pdfs-with-ai-and-python-part-1/ Search PDFs with AI and Python:…
-
Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI
The success of today’s AI applications requires not only model training (Model- centric) but also data engineering (Data-centric). In data-centric AI, active learning (AL) plays a vital role, but current AL tools can not perform AL tasks efficiently. To this end, this paper presents an efficient MLOps system for AL, named ALaaS (Active-Learning-as-a-Service). Specifically, ALaaS…
-
ALaaS: Active Learning as a Service.
Active Learning as a Service (ALaaS) is a fast and scalable framework for automatically selecting a subset to be labeled from a full dataset so to reduce labeling cost. It provides a out-of-the-box and standalone experience for users to quickly utilize active learning. https://github.com/MLSysOps/Active-Learning-as-a-Service MLSysOps/Active-Learning-as-a-Service: A scalable & efficient active learning/data selection system for everyone.…
-
Pandas DataFrame Tutorial – Beginner’s Guide to GPU Accelerated DataFrames in Python
This post is the first installment of the series of introductions to the RAPIDS ecosystem. The series explores and discusses various aspects of RAPIDS that allow its users solve ETL (Extract, Transform, Load) problems, build ML (Machine Learning) and DL (Deep Learning) models, explore expansive graphs, process geospatial, signal, and system log data, or use…