Petit thread dédié à "comment que ça marche les twitter-graph?" On va faire plein de screen du taff étape par étape, et parler un tout petit brin d'algo. Et on va reprendre Boris Hombourger pour illustrer, ça fait un exemple bien frappant.

🗓 Days 6 and 7 (yes, i forgot to post🤫) I have worked on aggregating DataFrames with pandas in #Python and also started to learn #R ! Also, I started to look at some datasets in order to start my personnal project. Can't wait to learn more😁 #100DaysOfCode

📆 Day 8 Today I've explored a fake news dataset and pre processed it for fake news prediction. I'll keep working on this project this week-end. Also it's not about programming but I started learning #Tableau, I wanna make fancy #datavisualization ! #100DaysOfCode #Python

🗓 Day 9 I solved some #Python problems, no big deal, just some practice. Now, time to enjoy the week-end! Have a great week-end ☺ #100DaysOfCode #Practice

You're incredible. Don't let anyone tell what you can and cannot do, go crush it.

Okay I've been away for a month, but i swear i kept coding! Holidays and univ projects took me a lot of time, but I'm back on track!

🗓 Day 10 - Distance metrics I've been working on similarities between questions and answers. I wanted to see if the various metrics allowed me to associate questions and answers based on their similarities. #100DaysOfCode #Python #NLP

🗓 Day 11 & 12 - Datadatadatadata ✅Some Twitter API practice ✅Data analysis on a Google Apps dataset for a DataCamp project + Sentiment analysis #100DaysOfCode #Python

My #mongodb journey starts today!

I just completed "Sonar Sweep" - Day 1 - Advent of Code 2021 adventofcode.com/2021/day/1 #AdventOfCode

I just completed "Dive!" - Day 2 - Advent of Code 2021 adventofcode.com/2021/day/2 #AdventOfCode

Clever paper — HyDE: Hypothetical Document Embeddings Instead of encoding the user's query to retrieve relevant documents, generate a "hypothetical" answer and encode that. Documents with right answers more similar to wrong answers than to questions. arxiv.org/abs/2212.10496

Happy Lunar NY 🎉 Just read Petar Veličković's "Everything is Connected". I spent most of 2022 studying Transformers for graphs and this paper intuitively connects most of what I've learned! 🔗: arxiv.org/abs/2301.08210 Here's an executive summary if you haven't caught it yet! 1/9

Transformer models: an introduction and catalog A super concise and brief overview of almost all popular Transformer models. Written well and provide pointers for recent advances in Transformer model architectures. arxiv.org/abs/2302.07730

Aligning Text-to-Image Models using Human Feedback abs: arxiv.org/abs/2302.12192

QLoRA: 4-bit finetuning of LLMs is here! With it comes Guanaco, a chatbot on a single GPU, achieving 99% ChatGPT performance on the Vicuna benchmark: Paper: arxiv.org/abs/2305.14314 Code+Demo: github.com/artidoro/qlora Samples: colab.research.google.com/drive/1kK6xasH… Colab: colab.research.google.com/drive/17XEqL1J…

La journée sur l'interdisciplinarité du DIM Patrimoines matériels à Sorbonne Université se poursuit sur une belle table ronde avec Diego Jarak Diego Jarak, Clément Levallois Clement Levallois / [email protected], Nedellec, Morgann et Darshan Sathiyanarayanan.

Understanding LLMs - Mapping the Mind of An AI Model The more we understand the inner workings of the LLM, the more we will be comfortable with it. Even top researchers don't completely understand how they work. Today, Anthropic released an important paper that help further our

Petit tour à VivaTech !

🏆🎮 Voici tous les jeux vidéo créés lors de l'EthicALL Game Jam à #VivaTech ! Après un événement intense et créatif dédié à la diversité et à l'inclusion, nous sommes ravis de vous présenter les jeux vidéo réalisés🌈🦾