mean pooling

implemented a new rendering component for latent scope's scatter plot. had to replace regl-scatterplot with d3-zoom + regl shaders so we could support mobile

I'll be at @unireps.bsky.social this Saturday presenting a new experimental pipeline to visually explore structured neural network representations. The core idea is to take thousands of prompts that activate a concept, and then cluster and draw them using MultiDiffusion. 🧵👇

am i missing something for handling image data in parquet files?

I can load a dataset from HF like:
dataset = load_dataset("Marqo/marqo-ge-sample", split='google_shopping')
df = pd.DataFrame(dataset)
but i need to convert the images to bytes if I want to do:
df.to_parquet("sample.parquet")

“They said it could not be done”. We’re releasing Pleias 1.0, the first suite of models trained on open data (either permissibly licensed or uncopyrighted): Pleias-3b, Pleias-1b and Pleias-350m, all based on the two trillion tokens set from Common Corpus.

CLIP search for 562K maps in Lib of Congress github.com/j-mahowald/c... Paper: 2024.computational-humanities-research.org/papers/paper... #chr2024

the algorithm is not some deity but a landscape, the feed is an uber ride across the manifold, only the windows are blacked out. what if you had a map of the algorithm? what if the UX of the feed let you look out of the window?

musing with @infowetrust.com
image from distill.pub/2017/aia/

Spent the day playing with this. I'm absolutely blown away @enjalot.bsky.social!

- Chose any embedding from HF
- Project with UMAP, cluster with HDBSCAN
- Use Ollama to label the clusters (Works incredibly well!)

😙👌📊📈📚

what's crazy to me is that so many of these can be run very efficiently on an M1 MacBook pro, and just fine on a VM with only CPU.
crazy how much value you can pull out of text without billions of parameters

If you're interested in embedding models for retrieval (search), clustering, classification, paraphrase mining, etc., then there's now 10,000 fully free and open source options on @hf.co via Sentence Transformers.

Check out the most popular ones here: huggingface.co/models?libra...

Hidden States is happening next week in SF!

It's a one-day unconference gathering researchers, designers, prototypers and engineers interested in pushing the boundaries of AI interfaces, going below the API and working with the hidden states.

hiddenstates.org

One way I've been thinking about ML models for some time is as a lens.

The weights are crystalized patterns whose structure emerges from the crushing pressures of backpropagation.

By shining a piece of data through this lens you see the patterns diffracted in the hidden states.

allow me to reintroduce myself!
I'm a prototyper and Data Alchemist interested in using machine learning for data visualization.

I'm building github.com/enjalot/late... using the lessons learned from co-authoring these 4 distill.pub papers

I'm here now! excited to meet up with folks in SF on Dec 3rd

Posting for Ian Johnson from other place - unconf Dec 3 in San Fran on embeddings/SAE etc

hiddenstates.org

👋