pascalzoleko @pascalzoleko

Be disruptive in the making Fürth, Germany Joined March 2019

Tweets

168
Followers

28
Following

79
Likes

296

Flexudy @flexudy

4 years ago

Let's be honest. ☝️ Large models like #huggingface transformers are expensive to run. In this FREE webinar, we present our cost-effective and yet scalable solution. eventbrite.com/e/deploy-trans… #Transformers #NLP #MachineLearning #webinar

0 1 2 0 0

pascalzoleko @pascalzoleko

4 years ago

I am normally all @GaryMarcus when it comes to AI, but oh boy, the harder it is to model a problem, the more I believe in @ylecun 's perspective. Strictly speaking of course. #ArtificialIntelligence #DeepLearning

0 3 0 0 0

pascalzoleko @pascalzoleko

4 years ago

Generating text with #Cheapity3 can prove to be a great and cheap resource for multilingual data generation. This simple frontend was built with 3 lines of code using @Gradio. The model is on the HF hub and Github. github.com/flexudy/NLPlay… huggingface.co/flexudy/cheapi…

0 2 5 0 0

Download Video

pascalzoleko @pascalzoleko

4 years ago

Looking for a cheap open-source multilingual (🇩🇪🇫🇷🇬🇧) alternative to " #gpt3 " ? In particular for academic text? Well, then Merry Christmas. 🎁😃. T5 available on @huggingface hub and on GitHub. huggingface.co/flexudy/cheapi… github.com/flexudy/NLPlay… #NLP #Transformers #DeepLearning

0 1 1 0 0

Download Image

AI at Meta @AIatMeta

4 years ago

We’re releasing the 1.0 version of Opacus, a #PyTorch training library that makes it easier for researchers to adopt differential privacy in #ML. Opacus 1.0 will accelerate differential privacy research in the field. Learn more: opacus.ai

6 63 276 0 34

Download Video

pascalzoleko @pascalzoleko

4 years ago

There is a new challenging EXtractive QA dataset. Question operators are based on didactic principles like Bloom's taxonomies. Want to see how well your QA model performs? Download it at: github.com/flexudy/ai-pow… or on the @huggingface hub. #NLP #DeepLearning

0 1 0 0 0

Download Image

pascalzoleko @pascalzoleko

4 years ago

🎯 The Conceptor is now available on the @huggingface 🤗 hub. Generate concepts or types E.g A dog is an animal. Ideal for Zero-shot tasks, logical reasoning, NER, QA or even text or intent classification pipelines. github.com/flexudy/natura… #NLP #ArtificialIntelligence

0 0 2 0 0

Download Image

pascalzoleko @pascalzoleko

4 years ago

Start building #NeuralNetworks backwards. The heart of true #ArtificialIntelligence is knowledge acquisition. Not consumption. I think it aligns well with people with this belief: "abstraction is the key".

0 1 0 0 0

Download Image

pascalzoleko @pascalzoleko

5 years ago

The field of #ArtificialIntelligence is conquered 😃? No more need for Transformers or GPUs? #DeepLearning #MachineLearning

0 1 0 0 0

Download Video

Flexudy @flexudy

5 years ago

Create #Flashcards in one click with #Flexudy. Simply choose the documents that you want to #study with and get right into it. Study on the go with the Flexudy app for Android and iOS or boost your study sessions with the Flexudy web app. Studying has never been this easy 🤓

0 2 2 0 0

Download Gif

Hugging Face @huggingface

5 years ago

🚨 NEW MODEL ALERT 🚨 Translate text to, or between 50 languages with mBART-50 from @FacebookAI ! 🇺🇳 One-to-Many model: translate from English to 49 other languages ↔️ Many-to-Many model: translation btw any pair of 50 languages

7 74 418 0 48

Download Image

pascalzoleko @pascalzoleko

5 years ago

Who is still waiting for the 4th edition of AIMA? #ArtificialIntelligence #MachineLearning

0 1 0 0 0

Download Image

pascalzoleko @pascalzoleko

5 years ago

In case you need a no-frills post-processor for facebook AI's amazing Wav2Vec 2.0: huggingface.co/flexudy/t5-sma… I fine-tuned a T5 model from the Hugging Face Hub using about ~120K paragraphs extracted from popular QA datasets. #naturallanguageprocessing #huggingface #flexudy

0 0 3 0 0

Download Gif

Flexudy @flexudy

5 years ago

Yet another two brilliant minds Sophia and Natasa have joined our #openinnovation team at #flexudy. Machine Teaching helps us improve our #AI making sure we are on top. Giving us a chance for new applications to cater to your needs Join us on our rise: flexudy.com/education/pipe/

0 2 5 0 0

Download Image

pascalzoleko @pascalzoleko

5 years ago

labeling data is a breeze with #labely @flexudy labely.netlify.app/home

0 0 1 0 0

Download Image

hardmaru @hardmaru

5 years ago

Beyond CUDA: GPU Accelerated Python for Machine Learning on Cross-Vendor Graphics Cards Made Simple A practical deep dive into GPU Accelerated Python on cross-vendor (not only NVIDIA) GPUs for building ML algorithms using “Vulkan Kompute” Python Framework redd.it/ju2em0

2 56 247 0 42

pascalzoleko @pascalzoleko

5 years ago

I sometimes see @huggingface's t5 tokenizer used like this: tokenizer.encode(some_long_text, max_length=512 ..) Di you know the size can double depending on the input 😅? Meaning sometimes, len(some_long_text.split()) ~= 2 x len(input_ids) so 256 tokens might be your max.

0 0 0 0 0

pascalzoleko @pascalzoleko

5 years ago

At @flexudy we started looking at simple approaches to improve the quality of T5 question-answer generation models on @huggingface using @deepset_ai's Haystack. The notebook is found here: colab.research.google.com/drive/1bpsSqCQ… Also accessible via @huggingface notebooks on github.

0 5 8 0 0

pascalzoleko @pascalzoleko

5 years ago

Made with much love 💚 🙌 by @CollinsKamgaing at the @flexudy Research Pipe. 💯 Open Sourced. Stay tuned at lnkd.in/ebMqEKg or flexudy.com/pipe. Interested in getting early access to a deployed version ? #naturallanguageprocessing #machinelearning #datalabeling

0 3 3 0 0

Download Video

pascalzoleko @pascalzoleko

5 years ago

How well do you unterstand what you read?🤯 What if your Smartphone could ask you questions like a teacher would? 🧐 🇨🇵🇬🇧🇩🇪 #flexudy #homeschooling #france2 #Education #edtechstartup #smartphone #universitylife