Datdanboi25 (Dan P)

reacted to Hoglet-33's post with 🔥 about 14 hours ago

Post

2220

Introducing VOID. A new research branch of basically AI.

VOID — Verification of Objectives, Intentions, and Deception.

We study what lies beneath the surface: objectives, intentions, and the possibility of deception in AI systems.

There isn't much to see yet.

That will change.

Follow us for updates:

@Hoglet-33

void-research

basically-ai

1 reply

·

reacted to their post with 🔥 1 day ago

Post

2884

100 likes on the Open SLM Leaderboard 🎉

176 models, 54 orgs, 5 benchmarks, and a whole community of support!

Thanks to everyone who’s contributed models, reported issues, suggested benchmark improvements, or used the leaderboard to compare and evaluate small language models.

It’s been awesome watching the leaderboard grow into a broader community resource for transparent and reproducible SLM evaluation.

Thank you all, and more to come 🚀

1 reply

·

reacted to CompactAI's post with ➕ 2 days ago

Post

4292

SLM Roundups, a weekly post where I summarize everything thats happened in the world of SLMs (or a majority of it)
Glint-Research/blog

1 reply

·

reacted to their post with ❤️ 4 days ago

Post

2884

100 likes on the Open SLM Leaderboard 🎉

176 models, 54 orgs, 5 benchmarks, and a whole community of support!

Thanks to everyone who’s contributed models, reported issues, suggested benchmark improvements, or used the leaderboard to compare and evaluate small language models.

It’s been awesome watching the leaderboard grow into a broader community resource for transparent and reproducible SLM evaluation.

Thank you all, and more to come 🚀

1 reply

·

posted an update 5 days ago

Post

2884

100 likes on the Open SLM Leaderboard 🎉

176 models, 54 orgs, 5 benchmarks, and a whole community of support!

Thanks to everyone who’s contributed models, reported issues, suggested benchmark improvements, or used the leaderboard to compare and evaluate small language models.

It’s been awesome watching the leaderboard grow into a broader community resource for transparent and reproducible SLM evaluation.

Thank you all, and more to come 🚀

1 reply

·

reacted to HannesVonEssen's post with 🔥 8 days ago

Post

4886

📣 HF Viewer now has a HF space! 🤗

embedl/hfviewer

Visualize any model directly on Hugging Face - now 4,727 graphs!

If you like it, feel free to give the space a heart to help it grow! ❤️

And you can reply with any feedback or feature requests here!

reacted to Hoglet-33's post with 😔 11 days ago

Post

3181

Today, we planned to release Pebble-50M and Pebble-50M-Chat to the world. Unfortunately, due to a few issues, that didn't go quite as planned.

What happened:
- Some data and benchmark results were lost or corrupted
- The models performed worse on benchmarks than our other Pebble models

Despite that, you can still find both models here:
Pebble-50M-beta: basically-experimental/Pebble-50M-beta
Pebble-50M-Chat-beta: basically-experimental/Pebble-50M-Chat-beta

There are still some interesting improvements in these models:
- Compatible with non-CUDA devices
- Vocabulary increased to 16K tokens
- Context length increased to 16K tokens

For now, there won't be any more Pebble releases for a while. We're going to take some time to experiment with other approaches and hopefully make the next generation a monumental leap over this one.

Follow for updates:
@Hoglet-33

basically-ai

basically-experimental

4 replies

·

reacted to Bc-AI's post with 🔥 15 days ago

Post

2499

Hello everyone!
Me and the team are working on G1-MINI and G1. Right now, G1-MINI is aimed at a launch in mid to late September, depending on how fast we fix the minor issues.
As for G1, it's looking like a late October to mid-November launch, based on current trajectory. If things go terribly wrong, we could postpone it to December, as we prefer to ship confidently, not ship a half-done dogs' breakfast of a model. 🤣
All dates could be changed at any moment, as we are high school students not full-time ML engineers 😅.
Other things to look out for is an overhaul of the UI and the information on my website. Thanks to my beta testers: @guardamarcos @Timmy6767 @MUK-IS-GOAT @smilyai-large-team @Sbui503 @Banaxi-Tech @Bc-AI @atom77777 @Harley-ml @Datdanboi25 @Fishtiks @smartdigitalnetworks @vovaRL @EmetTheGolum @juiceb0xc0de @ProCreations

3 replies

·

replied to Banaxi-Tech's post 16 days ago

Still using the XSA refresh gate, sweet!

reacted to Bc-AI's post with 🔥 16 days ago

Post

3772

Hello everyone! A small update on things:

1. G1 series status. G1 is training nicely, and the loss is dropping nicely. The metrics are publicly available and i made a small space you can use to see the nice graphs: hugging-science/Loss-Plot-G1-Large
G1-MINI is a lot slower in converging for reasons unknown yet, but we are investigating it.

2. I have built a small chat app for open SLMs here: ml-intern-explorers/slm-arena
Feel free to add your models in a pull request!

That's all for now, early G1 versions will be available for beta testers soon. Thanks to our beta testers: @guardamarcos @Timmy6767 @MUK-IS-GOAT @smilyai-large-team @Sbui503 @Banaxi-Tech @Bc-AI @atom77777 @Harley-ml @Datdanboi25 @Fishtiks @smartdigitalnetworks @vovaRL @EmetTheGolum @juiceb0xc0de @ProCreations

replied to Hoglet-33's post 17 days ago

Yeah I run 4096 vocab for my 5m models which I think is a nice sweetspot

reacted to AtAndDev's post with 🔥 17 days ago

Post

2827

SPECK 2 IS ALREADY OUT: specklabs/Speck2-140M

Pretrained on 4x more tokens than the previous releases (20b vs 5b).
Instruct tuned versions are coming soon.
Very interesting models are coming soon too (hint: super long context).

Thanks for everyone supporting!

3 replies

·

reacted to Banaxi-Tech's post with 🔥 17 days ago

Post

2894

We're excited to release BananaMind 2.1 Pico Preview!

It includes the first preview of our BananaMind 2.1 architecture!
This model gets near BananaMind 2 Micro performance at half the parameters and 37.5x less tokens!
Thats insane!

The current architectures includes about 500K parameters of the total 1.5M parameters in n-gram embeddings and the layer 2 is run twice.

It also includes XSA and the XSA refresh gate.

We're still going to improve the architecture in the final release.

Check it out at:

Follow us for more models:

BananaMind
@Banaxi-Tech
@vovaRL
@DedeProGames

3 replies

·

replied to KlondikeDev's post 17 days ago

How do I check if a number is prime in python?

replied to KlondikeDev's post 17 days ago

Gotta start prompt injecting it fr

replied to FlameF0X's post 18 days ago

Horray, WE ALL love attention

reacted to Banaxi-Tech's post with 🔥 18 days ago

Post

3445

Introducing BananaMindOS 3.0

- Complete modern UI redesign
- Adds support for Qwen3.5 0.8B, LFM2.5 230M,350M, SmolLM2 360M, Gemma 3 270M.
- Adds Q7,Q6,Q5,Q3,Q1 quantization formats with a easy to use precision slider
- And more!

The new UI includes:
- New 1024×768 High Quality interface.
- Photographic QOI background.
- Transparent BananaMind, CPU, cube, mouse, and Send icons.
- Proper bitmap cursor.
- Rounded translucent panels and cards.
- Modern model-loading progress window.
- Redesigned inference screen with response and prompt panels.
- Localized redraws for the cursor, clicks, loading progress, and precision slider.

Notice: Qwen3.5 0.8B currently generates garbled text, it will be fixed tomorrow.

See it for yourself
Now Available at https://github.com/BananaMind/BananaMindOS

Prebuild ISOs coming soon!

(also press ? + G if you want to load try to load a 6MB RAM model on 5MB may break)

7 replies

·

replied to FlameF0X's post 18 days ago

Do you use linear or regular attention?

replied to KlondikeDev's post 18 days ago

Well, I still think that what’s the point of FOSS if it isn’t allowed to be cloned? Also, Dan, you’re right — he probably does just work hard. He is incredibly talented.

And for the Open SLM Leaderboard, I still don’t want to be on a closed-source… anything, regardless. I have nothing against it, it just isn’t FOSS.

Yeah fair enough, its a respectable mission, and while we'd love to have your models, we feel like every author should be able to decide where and how their models get displayed!

replied to KlondikeDev's post 18 days ago

TBF I dont even think he has all that compute, he just works hard

I'm working hard but you don't see me producing 5 models every week.

True altho I think he does his cleverly, seems to train the models in batches of same arch saame datasets

Dan P

AI & ML interests

Recent Activity

Organizations

Dan P

AI & ML interests

Recent Activity

Organizations

Datdanboi25's activity