excited to hear your thoughts/ideas! right now its pretty simple: just take the last N lines of conversation. but a very natural extension to determine N dynamically based on their length
CODE
-
50 Free Public Datasets for Machine Learning Practice
By
–
Best Public Datasets for Machine Learning and Data Science. Here are 50 datasets you can access right now without paying a single cent. Pair them with Google Colab, and you can start practicing machine learning today. https://
pub.towardsai.net/best-datasets-
for-machine-learning-data-science-computer-vision-nlp-ai-c9541058cf4f
… -
Elixir Now Supports AI Models from GPT2 to Stable Diffusion
By
–
welcomes @elixirlang ! Elixir now supports models on the Hub, from GPT2 to Stable Diffusion We're excited to see what the community builds with this! @josevalim
, the creator of Elixir, wrote this nice blog post -
Modal launches infrastructure platform with code-first configuration approach
By
–
Modal is finally coming out of the least secretive stealth mode ever: and look at this painless declaration of infra: “there is no configuration in Modal — everything is in code”
-
AlphaCode Published in Science Magazine
By
–
Proud to see AlphaCode published on @ScienceMagazine and above all proud of the AlphaCode team for their inspiring and pioneering work, and for their collaborative spirit and inclusive practices. https://t.co/lWHmHoR9Yd
— Nando de Freitas (@NandoDF) 8 décembre 2022Proud to see AlphaCode published on @ScienceMagazine and above all proud of the AlphaCode team for their inspiring and pioneering work, and for their collaborative spirit and inclusive practices.
-
Generalist Neural Net Implements Classical Computer Science Algorithms
By
–
Impressive to see a generalist neural net implementation of so many of the classical algorithms taught in undergraduate computer science.
-
AlphaCode AI System Published in Science Magazine
By
–
So proud of the team behind #AlphaCode, published today @ScienceMagazine
! Paper: http://
scim.ag/Nn -
Low-code ML approaches for building deep learning image classification models
By
–
Low-code declarative #ML approaches make it easy to build complex #deeplearning models in minutes. Don't miss our webinar for a deep dive into how to build an end-to-end image classification system. And, it's a fun use case "Santavision"! https://
pbase.ai/3uvA046 -
Whisper Model 8-bit Loading: Memory-Efficient Inference
By
–
Like all the models on the transformers models, all Whisper checkpoints can be loaded in a memory-efficient way! With load_in_8bit=True you can load the model with 8-bit precision. P.S. You can load a Whisper-large model < 6.6 gig VRAM
-
Whisper: Transcribe Audio and YouTube Videos with AI
By
–
Transcribe audio and YouTube videos with any pre-trained or fine-tuned Whisper checkpoint on the hub! All you need to do is duplicate this space and update your checkpoint name and language! https://
huggingface.co/spaces/whisper
-event/whisper-demo
…