README
๐
AI & ML interests
Connecting individuals with innovation: Emancipating and Truly Federalizing Private Intelligence
Recent Activity
fuzzy-mittenzย
updated a
Space 8 days ago
Post
390
๐Hey there folks ,
I wanted to use a Jev model in a practical way , and I came up with this OCR pipeline using decision-models to evaluate OCR quality .
Check it out :
Tonic/OCR-with-JEV
I wanted to use a Jev model in a practical way , and I came up with this OCR pipeline using decision-models to evaluate OCR quality .
Check it out :
Tonic/OCR-with-JEV
- 4 replies
takarajordanย
posted an update 16 days ago
Post
92
Super impressed with the UltraBERT team at @dmis-lab โ @affjljoo3581 , @Taewhoo and Jaewoo Kang โ for continuing to push encoders forward. Really impressive work!
I knocked up an MoE version on a single A100, entirely for fun: UltraBERT-Embed-MoE-8x.
8 experts per routed layer, 2 active per token. Works pretty well in my small retrieval tests!
Huge credit to the original team for making this possible.
Original: dmis-lab/UltraBERT-Embed-150M
MoE: takarajordan/UltraBERT-Embed-MoE-8x
I knocked up an MoE version on a single A100, entirely for fun: UltraBERT-Embed-MoE-8x.
8 experts per routed layer, 2 active per token. Works pretty well in my small retrieval tests!
Huge credit to the original team for making this possible.
Original: dmis-lab/UltraBERT-Embed-150M
MoE: takarajordan/UltraBERT-Embed-MoE-8x
fuzzy-mittenzย
updated a
collection about 1 month ago
fuzzy-mittenzย
updated 2
collections about 2 months ago
fuzzy-mittenzย
updated a
collection 2 months ago
Post
103
Released MAiRY Star, a companion/perosna Ai fine tuned with SFT Studio Pro dataset , no RLHF or reward optimization. Access at https://triadai.tech
Q-bertย
authored a
paper 3 months ago
suayptalhaย
submitted a
paper to Daily Papers 3 months ago
suayptalhaย
authored a
paper 3 months ago
suayptalhaย
authored a
paper 4 months ago
Post
552
Shipped v0.1.2 of vtx โ a minimalist coding agent for the terminal.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test")
โ 49 LLM provider gateways, all declared in a single provider.yaml
โ 5 core tools (read / edit / write / bash / find) plus web search and fetch
โ Session tree with compaction, handoff, and resume
โ AGENTS.md / CLAUDE.md auto-discovery
โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands
โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono โ same principles, pure Python, no transpiled runtime.
What ships out of the box:
โ Textual TUI + headless CLI (vtx -p "fix the failing test")
โ 49 LLM provider gateways, all declared in a single provider.yaml
โ 5 core tools (read / edit / write / bash / find) plus web search and fetch
โ Session tree with compaction, handoff, and resume
โ AGENTS.md / CLAUDE.md auto-discovery
โ Skills system โ drop SKILL.md files in .agents/skills/ and they become slash commands
โ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
โ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Post
3,562
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
- 3 replies
Post
231
Introducing
Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model.
It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint.
The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model.
fblgit/haremb-privacy-filter-opennemo
I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model.
Contact [email protected]
HarEmb - PII a single-transformer-block distilled layer from OpenMed PII Privacy filter.Its a very tiny model that reaches comparable results at PII classification thru viterbi BIOES decoding, harnessing 98%~ the original model performance while being a tiny fraction of the base model.
It doubles the performance tk/s, reduces the active params dramatically and the VRAM footprint.
The evaluation & benchmarking is within the model repository and can be reproduced. I trained it with an RTX4090 without issues and it is compatible with OpenMed suite and a in-place replacement for openai privacy-filter model.
fblgit/haremb-privacy-filter-opennemo
I'm looking for people who wants to co-author/contribute/endorse HarEmb research and the technical paper for the model.
Contact [email protected]
Sri-Vigneshwar-DJย
posted an update 7 months ago
Post
243
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) โ 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** ยท GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
โ Info-extraction: **0.942**
โ Knowledge-update: **0.714**
โ Multi-session: **0.606**
โ Temporal: **0.477** โ the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense ยท adaptive temporal decay ยท embedded (no server) ยท p50 = 0.19ms ยท MIT
Raw results + audit JSONs: Hawky-ai/longmemeval-results
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) โ 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** ยท GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
โ Info-extraction: **0.942**
โ Knowledge-update: **0.714**
โ Multi-session: **0.606**
โ Temporal: **0.477** โ the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense ยท adaptive temporal decay ยท embedded (no server) ยท p50 = 0.19ms ยท MIT
pip install feather-dbRaw results + audit JSONs: Hawky-ai/longmemeval-results
Post
4,528
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
Post
3,770
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
suayptalhaย
authored a
paper 7 months ago