hey dark , actually if you're keen it wouold be nice to get this into mobile apps , but i do need help with the ux
Joseph [open/acc] Pollack PRO
Tonic
AI & ML interests
๐คMaking robots to help people learn things quicker ๐ฉ๐ปโ๐๐
Recent Activity
repliedto their post about 2 hours ago
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: https://huggingface.co/datasets/NuTonic/sat-vl-sft-training-ready-v1
- Model: https://huggingface.co/NuTonic/lspace
- Training: https://huggingface.co/spaces/NuTonic/lspace-trackio
- Evals: https://huggingface.co/datasets/NuTonic/Patagonia_Eval liked a dataset about 6 hours ago
fpvlabs/stera-10m posted an update 3 days ago
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: https://huggingface.co/datasets/NuTonic/sat-vl-sft-training-ready-v1
- Model: https://huggingface.co/NuTonic/lspace
- Training: https://huggingface.co/spaces/NuTonic/lspace-trackio
- Evals: https://huggingface.co/datasets/NuTonic/Patagonia_EvalOrganizations
replied to their post about 2 hours ago
posted an update 3 days ago
Post
2239
๐๐ปโโ๏ธ Hey there folks ,
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
Turns out : if we predict ๐ earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery ๐ฐ๏ธbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize ๐กearth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
At least that's the concept !
check out the blog : https://huggingface.co/blog/Tonic/save-patagonia-by-predicting-earth
- Collection: https://huggingface.co/collections/NuTonic/earth-observation-with-temporal-and-general-understanding
- Code: https://github.com/Josephrp/Nutonic
- Dataset: NuTonic/sat-vl-sft-training-ready-v1
- Model: NuTonic/lspace
- Training: NuTonic/lspace-trackio
- Evals: NuTonic/Patagonia_Eval
- 2 replies
reacted to danielhanchen's post with โค๏ธ 3 days ago
Post
5264
Weโre excited to announce that Unsloth has joined the PyTorch Ecosystem! ๐ฅ๐ฆฅ
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! ๐
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! ๐
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
- 2 replies
reacted to unmodeled-tyler's post with ๐ 3 days ago
Post
2908
The UFO/UAP Dataset is complete!
unmodeled-tyler/DoW-UFO-UAP-1
The most recent release from the Department of War is there up in full and ready for analysis!
The dataset ships with an Hermes Agent Skill so you can quickly and easily start parsing through the data immediately.
Go chase some anomalies! ๐
unmodeled-tyler/DoW-UFO-UAP-1
The most recent release from the Department of War is there up in full and ready for analysis!
The dataset ships with an Hermes Agent Skill so you can quickly and easily start parsing through the data immediately.
Go chase some anomalies! ๐
reacted to cesear64's post with ๐ 3 days ago
Post
4015
Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute.
The method โ vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon โ generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
๐ Blog: https://huggingface.co/blog/MEYNG/sangoai
๐ฆ Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages โ Ewondo, Lingala, Wolof next on our roadmap.
The method โ vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon โ generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.
๐ Blog: https://huggingface.co/blog/MEYNG/sangoai
๐ฆ Dataset: MEYNG/sango-vocabulary
Would especially value feedback from anyone working on other low-resource African languages โ Ewondo, Lingala, Wolof next on our roadmap.
- 1 reply
posted an update 19 days ago
Post
4183
๐๐ปโโ๏ธ Hey there folks,
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Check this one out :
NuTonic/sat-bbox-metadata-sft-v1
the goal is to be able to train vision models on multiple images for remote sensing analysis with one shot .
hope you like it ! ๐
- 2 replies
posted an update 24 days ago
Post
3579
๐๐ปโโ๏ธ Hey there folks ,
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
I'm sharing huggingface's largest dataset of annotated statelite images today.
check it out here : NuTonic/sat-image-boundingbox-sft-full
I hope you like it , the idea is to be able to use this with small vision models ๐
reacted to prometechinc's post with ๐ about 2 months ago
Post
2305
Cicikuล v4-5B (POFUDUK Edition) is a next-generation compact language model engineered for high-efficiency reasoning, adaptive intelligence, and behavioral coherence. Built on the Gemma 4B IT foundation and enhanced through advanced LoRA optimization and selective layer reconstruction, this model delivers powerful performance without the overhead of massive parameter counts.
๐ Explore the model: pthinc/pofuduk_cicikus_v4_5B
๐ง Why Cicikuล?
In a world dominated by massive LLMs, Cicikuล takes a different path:
โก Fast & Efficient โ Designed for edge deployment and low-resource environments
๐ฏ High Reasoning Accuracy โ Strong results across MMLU, GSM8K, HumanEval, and more
๐งฉ Behavior-Aware Intelligence โ Powered by the Behavioral Consciousness Engine (BCE)
๐ Low Hallucination Rate โ ~3% with built-in ethical filtering
๐ Multilingual Capable โ Optimized for English and Turkish
๐ Explore the model: pthinc/pofuduk_cicikus_v4_5B
๐ง Why Cicikuล?
In a world dominated by massive LLMs, Cicikuล takes a different path:
โก Fast & Efficient โ Designed for edge deployment and low-resource environments
๐ฏ High Reasoning Accuracy โ Strong results across MMLU, GSM8K, HumanEval, and more
๐งฉ Behavior-Aware Intelligence โ Powered by the Behavioral Consciousness Engine (BCE)
๐ Low Hallucination Rate โ ~3% with built-in ethical filtering
๐ Multilingual Capable โ Optimized for English and Turkish
reacted to h4's post with ๐ฅ๐๐โ๐ 2 months ago
Post
256
finding https://github.com/meta-introspector/monster/blob/9a368b1dd58e72ed4a466f81f74ab2ea95c26927/experiments/bott_periodicity/monster_walk.tex#L82 I sent this to my old math prof
You can remove these primes in groups from the monster in the 10fold way
1 & 0 & 8080 & 4 & 8 \\
2 & 4 & 1742 & 4 & 4 \\
3 & 8 & 479 & 3 & 4 \\
4 & 11 & 451 & 3 & 4 \\
5 & 14 & 2875 & 4 & 4 \\
https://x.com/introsp3ctor/status/2018078520321179935
You can remove these primes in groups from the monster in the 10fold way
1 & 0 & 8080 & 4 & 8 \\
2 & 4 & 1742 & 4 & 4 \\
3 & 8 & 479 & 3 & 4 \\
4 & 11 & 451 & 3 & 4 \\
5 & 14 & 2875 & 4 & 4 \\
https://x.com/introsp3ctor/status/2018078520321179935
reacted to OzTianlu's post with ๐ 2 months ago
Post
1975
We deleted the Embedding Layer -- INTRO Our Collins-Embedding-3M
NoesisLab/Collins-Embedding-3M
Most "small" models are just giant vocab tables in a trench coat. Collins-3M changes that. By using 2-Universal Hashing and Chernoff-bound noise suppression, weโve collapsed the embedding space into a fixed O(1) hash-map.
* STSB: 0.7114 (Beating many 100M+ models)
* Size: 3M (Edge-ready, IoT-ready)
* Tech: Randomized Sign-Hashing + RoPE positional injection.
Built by NoesisLab
NoesisLab/Collins-Embedding-3M
Most "small" models are just giant vocab tables in a trench coat. Collins-3M changes that. By using 2-Universal Hashing and Chernoff-bound noise suppression, weโve collapsed the embedding space into a fixed O(1) hash-map.
* STSB: 0.7114 (Beating many 100M+ models)
* Size: 3M (Edge-ready, IoT-ready)
* Tech: Randomized Sign-Hashing + RoPE positional injection.
Built by NoesisLab
reacted to their post with ๐ฅ 3 months ago
Post
3723
๐ค Who would win ?
- a fully subsidized ai lab
- 3 random students named
kurakurai ?
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- a fully subsidized ai lab
OR - 3 random students named
demo : Tonic/fr-on-device
if you like it give the demo a little star and send a shoutout to : @MaxLSB @jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
- 4 replies
replied to ZennyKenny's post 3 months ago
nothing is perfect but at least they care about their community experience at huggingface :-)
replied to ZennyKenny's post 3 months ago
this was actually fantastic news to hear though :-) secretly glad about it
reacted to ZennyKenny's post with ๐ 3 months ago
Post
1997
๐ซ Brutal! Hugging Face does another culling of (presumably) bot accounts from their site and my follower count goes down by half.
๐ TFW my content and models only appeal to bots. Whoโs got the current best AI girlfriend app guys?
๐ TFW my content and models only appeal to bots. Whoโs got the current best AI girlfriend app guys?
- 11 replies
replied to their post 3 months ago
In short, the students won. They did so by fine-tuning LFM2. LFM2 is a foundation built by Liquid AI. Liquid AI is a $2 billion startup from MIT.
the total budget of the students was zero . the total budget required (currently) for someone with no access to a computer is zero : https://huggingface.co/unsloth-jobs
i think that's cool ๐๐ป
replied to their post 3 months ago
it's actually not a mystery why a well-ressourced language like french would actually get history made by highschoolers' side project : a pareto frontier they've currently held for almost six months now ...
their supreme reign will continue until ressource allocation improves.