Tonic/huggingface-static-5f43a1-bucket
0 Bytes
Joseph [open/acc] Pollack PRO
Tonic
AI & ML interests
π€Making robots to help people learn things quicker π©π»βππ
Recent Activity
published a bucket about 1 hour ago
Tonic/huggingface-static-5f43a1-bucket published a bucket about 1 hour ago
Tonic/huggingface-static-6f0767-bucket published a bucket about 3 hours ago
Tonic/huggingface-static-4873c6-bucketOrganizations
Posts 61
Post
3339
ππ»ββοΈ Hey there folks ,
Turns out : if we predict π 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 π°οΈbasically 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 π‘earth-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 π 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 π°οΈbasically 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 π‘earth-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
Articles 4
Article
3
Teaching Satellites to Remember: Patagonia as a Testbed for Predictive Earth Intelligence
spaces 167
pinned
Runtime error
Agents
6
Baguettotron vs Luth models
π¦
fully subsidized versus non-subsidized fr understanding
pinned
Sleeping
Agents
9
Salamandra 7B
π¦
multilingual instruct model verifiably trained on open data
pinned
Running on Zero
Agents
7
L Operator Demo
π
demo of l-operator with no commands
pinned
Running on Zero
MCP
42
Moonshot Math
π
Formal reasoning model that can reason and prove theorems
pinned
Running on Zero
MCP
79
Advanced Stock Prediction Analysis with Amazon Chronos
π
stock prediction with Amazon/Chronos
Running
Agents
Lfm25 Wolof Trackio
π―
Display an interactive tracking dashboard
models 30
Tonic/Huihui-Qwen3.8-27B-abliterated-mlx-4Bit
Image-Text-to-Text β’ 27B β’ Updated β’ 437
Tonic/adaption_emir_reporting_code_gen
Updated β’ 6
Tonic/sharing-stuff-with-frens
Updated β’ 1
Tonic/l-operator-instruct
Updated β’ 1
Tonic/voxtral-finetune-20250913_145448
Updated β’ 15
Tonic/sending_files_online_for_my_friends
Updated
Tonic/l-android-control
Image-Text-to-Text β’ Updated β’ 1
Tonic/g-operator
Image-Text-to-Text β’ Updated β’ 2
Tonic/l-operator
Image-Text-to-Text β’ 2B β’ Updated
Tonic/med-gpt-oss-20b
Text Generation β’ 21B β’ Updated β’ 28 β’ 7
datasets 45
Tonic/adaption-emir-reporting-code-gen-v5
Viewer β’ Updated β’ 53.2k β’ 25
Tonic/adaption-emir-reporting-code-gen-v4
Viewer β’ Updated β’ 19.2k β’ 25
Tonic/adaption-emir-reporting-code-gen-v3
Viewer β’ Updated β’ 19.2k β’ 25
Tonic/multilingual-EMIR-reporting-csv
Viewer β’ Updated β’ 19.2k β’ 16
Tonic/multilingual-EMIR-reporting-jsonl
Viewer β’ Updated β’ 19.2k β’ 34
Tonic/multilingual-EMIR-reporting-parquet-mixed
Viewer β’ Updated β’ 19.2k β’ 409
Tonic/adaption-emir-reporting-qa
Viewer β’ Updated β’ 139 β’ 30
Tonic/adaption-emir-reporting-code-gen-v2
Viewer β’ Updated β’ 1.99k β’ 23
Tonic/adaption-emir-reporting-code-gen-v1
Viewer β’ Updated β’ 1.99k β’ 21
Tonic/adaption-emir-reporting-code-gen
Viewer β’ Updated β’ 361 β’ 21