Catégorie : Notes
-
Machine Learning Mastery
https://machinelearningmastery.com/
-
Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon S ageMaker
https://huggingface.co/blog/sagemaker-distributed-training-seq2seq Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker Tutorial We will use the new Hugging Face DLCs and Amazon SageMaker extension to train a distributed Seq2Seq-transformer model on the summarization task using the transformers and datasets libraries, and then upload the model to huggingface.co and test it.. As distributed training…
-
Cooperative AI: machines must learn to find common ground
https://www.nature.com/articles/d41586-021-01170-0
-
Conversations Gone Awry: Detecting Early Signs of Conversational Failure
https://arxiv.org/abs/1805.05345
-
Summer of Language Models 21
Summer of Language Models 21 https://bigscience.huggingface.co/en/#!index.md
-
atoti is a free Python BI analytics platform
https://www.atoti.io/ BI analytics. Boosted. – atoti atoti is a free Python BI analytics platform for Quants, Data Analysts, Data Scientists & Business Users to collaborate better, analyze faster and translate their data into business KPIs www.atoti.io
-
Practical SQL for Data Analysis | Haki Benita
https://hakibenita.com/sql-for-data-analysis
-
Deploy T5 transformer model as a serverless FastAPI service on Google Cloud Run – YouTube
https://m.youtube.com/watch?v=OzV21spbCfI
-
3 May, 2021 08:29
https://martinfleischmann.net/clustergam-visualisation-of-cluster-analysis/
-
GitHub – mljar/mljar-supervised: Automated Machine Learning Pipeline with Feature Engineering and Hyper-Parameters Tuning
https://github.com/mljar/mljar-supervised
-
OpenAI-powered Linux shell uses AI to Do What You Mean
https://riveducha.onfabrica.com/openai-powered-linux-shell OpenAI-Powered Linux Shell This is a basic Python shell (really, it’s a fancy wrapper over the system shell) that takes a task and asks OpenAI for what Linux bash command to run based on your description. riveducha.onfabrica.com
-
Semantic Search On Documents – Pratik’s Pakodas 🍿
https://pakodas.substack.com/p/semantic-search-on-documents
-
GitHub – UKPLab/sentence-transformers: Sentence Embeddings with BERT & XLNet
https://github.com/UKPLab/sentence-transformers
-
GitHub – cupy/cupy: A NumPy-compatible array library accelerated by CUDA
https://github.com/cupy/cupy
-
22 April, 2021 07:23
https://huggingface.co/blog/bert-cpu-scaling-part-1
-
A Curated List of 57 Amazing GitHub Repositories for Every Python Developer
https://betterprogramming.pub/a-curated-list-of-57-amazing-github-repositories-for-every-python-developer-67dc2cd8d0bc
-
MBRL-Lib
https://github.com/facebookresearch/mbrl-lib GitHub – facebookresearch/mbrl-lib: Library for Model Based RL MBRL-Lib. mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms. It provides easily interchangeable modeling and planning components, and a set of utility functions that allow writing model-based RL algorithms with only a few lines of code. github.com
-
SummVis is an interactive visualization tool for abstractive summarization systems, supporting analysis of models, data, and evaluation metrics.
https://github.com/robustness-gym/summvis robustness-gym/summvis SummVis is an interactive visualization tool for text summarization. – robustness-gym/summvis github.com
-
NVIDIA, Stanford & Microsoft Propose Efficient Trillion-Parameter Language Model Training on GPU Clusters | by Synced | SyncedReview | Apr, 2021 | Medium
https://medium.com/syncedreview/nvidia-stanford-microsoft-propose-efficient-trillion-parameter-language-model-training-on-gpu-7e415235313c
-
GooAQ 🥑: Google Answers to Google Questions!
https://github.com/allenai/gooaq GitHub – allenai/gooaq: Question-answers, collected from Google where the questions question are collected via Google auto-complete. The answers responses (short_answer and answer) were collected from Google’s answer boxes.The answer types (answer_type) are inferred based on the html content of Google’s response.Here is the dominant types in the current dataset: feat_snip: explanatory responses; the majoriy…
-
DALL-E in Pytorch
https://lnkd.in/gqe7Ckr lucidrains/DALLE-pytorch Implementation / replication of DALL-E, OpenAI’s Text to Image Transformer, in Pytorch – lucidrains/DALLE-pytorch lnkd.in
-
OCTIS : Optimizing and Comparing Topic Models is Simple!
https://github.com/mind-lab/octis GitHub – MIND-Lab/OCTIS: OCTIS: a python package to optimize and evaluate topic models OCTIS. OCTIS (Optimizing and Comparing Topic models Is Simple) aims at training, analyzing and comparing Topic Models, whose optimal hyper-parameters are estimated by means of a Bayesian Optimization approach. github.com
-
Analysis of Twitter Users’ Lifestyle Choices using Joint Embedding Model
[2104.03189] Analysis of Twitter Users’ Lifestyle Choices using Joint Embedding Model Multiview representation learning of data can help construct coherent and contextualized users’ representations on social media. This paper suggests a joint embedding model, incorporating users’ social and textual information to learn contextualized user representations used for understanding their lifestyle choices. We apply our model…
-
PyCaret is an open-source, low-code machine learning library and end-to-end model management tool built in Python for automating ML worflows | Towards Data Science
https://towardsdatascience.com/multiple-time-series-forecasting-with-pycaret-bc0a779a22fe
-
How to deploy Machine Learning models as a Microservice using FastAPI | by Ashutosh Tripathi | Towards Data Science
https://towardsdatascience.com/how-to-deploy-machine-learning-models-as-a-microservice-using-fastapi-b3a6002768af
-
GANcraft – Unsupervised 3D Neural Rendering of Minecraft Worlds
https://nvlabs.github.io/GANcraft/ GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds nvlabs.github.io
-
News Feed ranking, powered by machine learning – Facebook Engineering
https://engineering.fb.com/2021/01/26/ml-applications/news-feed-ranking/
-
Awesome Tricks And Best Practices From Kaggle
https://www.kdnuggets.com/2021/04/awesome-tricks-best-practices-kaggle.html Awesome Tricks And Best Practices From Kaggle – KDnuggets By Bex T., Top Writer in AI Weekly Awesome Tricks And Best Practices From Kaggle . About This Project Kaggle is a wonderful place. It is a gold mine of knowledge for data scientists and ML engineers. www.kdnuggets.com
-
15 April, 2021 20:26
https://towardsdatascience.com/pycaret-2-2-is-here-whats-new-ad7612ca63b
-
15 April, 2021 20:24
http://haacked.com/archive/2021/04/14/https-for-azure-functions/?utm_content=buffercce55&utm_medium=social&utm_source=linkedin.com&utm_campaign=buffer
-
textflint/textflint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
https://github.com/textflint/textflint
-
semi-technologies/weaviate: Weaviate is a cloud-native, modular, real-time vector search engine
https://github.com/semi-technologies/weaviate
-
apache/superset: Apache Superset is a Data Visualization and Data Exploration Platform
https://github.com/apache/superset
-
The Super Duper NLP Repo
https://notebooks.quantumstat.com/
-
Handy-Dandy Python Modules For Data Processing | by Emmett Boudreau | Apr, 2021 | Towards Data Science
https://towardsdatascience.com/handy-dandy-python-modules-for-data-processing-3a85d6806d39
-
open-mmlab/mmocr: OpenMMLab Text Detection, Recognition and Understanding Toolbox
https://github.com/open-mmlab/mmocr
-
neo4j/graphql: A GraphQL to Cypher query execution layer for Neo4j and JavaScript GraphQL implementations.
https://github.com/neo4j/graphql
-
What is MLOps? Machine Learning Operations Explained
https://www-freecodecamp-org.cdn.ampproject.org/c/s/www.freecodecamp.org/news/what-is-mlops-machine-learning-operations-explained/amp/
-
Words in context: tracking context-processing during language comprehension using computational language models and MEG
https://www.biorxiv.org/content/10.1101/2020.06.19.161190v1.full Words in context: tracking context-processing during language comprehension using computational language models and MEG www.biorxiv.org
-
DeepMind, Microsoft, Allen AI & UW Researchers Convert Pretrained Transformers into RNNs, Lowering Memory Cost While Retaining High Accuracy | by Synced | SyncedReview | Apr, 2021 | Medium
https://medium.com/syncedreview/deepmind-microsoft-allen-ai-uw-researchers-convert-pretrained-transformers-into-rnns-lowering-806b94bf0521
-
Layout-Parser/layout-parser: A Python Library for Document Layout Understanding
https://github.com/Layout-Parser/layout-parser
-
POT: Python Optimal Transport
https://github.com/PythonOT/POT GitHub – PythonOT/POT: POT : Python Optimal Transport * add some text + discussion sinkhorn * stating wrk on why POT * fix sphinx warnings + make html-noplot * discussion when not to use POT * add discussion which sinkhorn * edits on quickstart * more * remove warnings :any: * more * done…
-
How to make an awesome Python package in 2021
https://antonz.org/python-packaging/ How to make an awesome Python package in 2021 | Anton Zhiyanov build.yml. GitHub runs tests via tox – just as we did.tox-gh-actions package and USING_COVERAGE settings ensure that tox uses the same Python version as GitHub Actions themself, as required by strategy.matrix (I learned this clever trick from Hynek Schlawak).. The last step…
-
French sentiment analysis with BERT
https://github.com/TheophileBlard/french-sentiment-analysis-with-bert GitHub – TheophileBlard/french-sentiment-analysis-with-bert: How good is BERT ? Comparing BERT to other state-of-the-art approaches on a French sentiment analysis dataset French sentiment analysis with BERT. How good is BERT ? Comparing BERT to other state-of-the-art approaches on a large-scale French sentiment analysis dataset 📚. The contribution of this repository is threefold. github.com
-
PAIR-code/lit: The Language Interpretability Tool: Interactively analyze NLP models for model understanding in an extensible and framework agnostic interface.
https://github.com/PAIR-code/lit/
-
Feature-engine: A new open source Python package for feature engineering
https://trainindata.medium.com/feature-engine-a-new-open-source-python-package-for-feature-engineering-29a0ab88ea7c Feature-engine: A new open source Python package for feature engineering Feature-engine is an open source Python library with the most exhaustive battery of transformers to engineer features for machine learning. trainindata.medium.com
-
TextFlint
Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing https://github.com/textflint/textflint
-
6 April, 2021 01:06
https://rebecca-vickery.medium.com/data-science-learning-resources-ef034c8f2713