unmodeled-tyler (Tyler Williams)

reacted to their post with 🚀 about 11 hours ago

Post

325

Just started a fun project!

unmodeled-tyler/DoW-UFO-UAP-1

I'm getting the recently released DoW UFO/UAP documents (https://war.gov/ufo) cleaned and converted into a dataset here on Hugging Face!

There 161 different files in the gov release (pdfs, images, videos, audio, etc) and my current plan is to do it all in 1 dataset with 4 different shards - that way you can just call whichever tables you want/need when you import the dataset.

This is an ongoing project (I'm doing it on the side + my regular projects) so it's a bit of a growing entity. I'll also continuously refine the data over time to make sure it's as clean as possible.

Check it out! Who knows what you'll find in there?

2 replies

·

updated a dataset about 12 hours ago

unmodeled-tyler/DoW-UFO-UAP-1

Viewer • Updated about 8 hours ago • 4.93k • 242 • 1

replied to their post about 12 hours ago

A thought keeps occurring to me throughout this project so far:

"What happens to declassified data when the public suddenly has tools powerful enough to actually understand it?"

For instance, these types of record releases are not new - the US Government has been declassifying and releasing records since its inception. What IS new is the average person's ability to parse, synthesize, and make connections that may not have been previously possible by a single human - particularly in tandem with frontier AI that can complete work that before would have required a specialized research team.

A single file within 161 total file release could contain upwards of 300 different pages. All of those pages are more or less loosely in a logical order - but not necessarily. The released records follow the same archival conventions that are used internally by the government. It is by its very nature, "not for public consumption." It is not made to be publicly comprehensible. If you aren't familiar with those systems, you're cooked.

What access to AI systems allows us to do is take those previously muddy, incomprehensible (but very valuable!) releases and make them legible to the average person.

If then, this data becomes comprehensible to more people, we now have even more humans thinking about the very strange problems that may lie buried deep inside - maybe some of those humans will make a connection that was missed the first time? What if that previously missed connection leads to a groundbreaking discovery?

Either way, this is bigger than UFO/UAP documents. It applies to any public data that has been available IN THEORY but inaccessible in practice.

Happy building!

posted an update about 13 hours ago

Post

325

Just started a fun project!

unmodeled-tyler/DoW-UFO-UAP-1

I'm getting the recently released DoW UFO/UAP documents (https://war.gov/ufo) cleaned and converted into a dataset here on Hugging Face!

There 161 different files in the gov release (pdfs, images, videos, audio, etc) and my current plan is to do it all in 1 dataset with 4 different shards - that way you can just call whichever tables you want/need when you import the dataset.

This is an ongoing project (I'm doing it on the side + my regular projects) so it's a bit of a growing entity. I'll also continuously refine the data over time to make sure it's as clean as possible.

Check it out! Who knows what you'll find in there?

2 replies

·

liked a dataset about 18 hours ago

unmodeled-tyler/DoW-UFO-UAP-1

Viewer • Updated about 8 hours ago • 4.93k • 242 • 1

published a dataset about 18 hours ago

unmodeled-tyler/DoW-UFO-UAP-1

Viewer • Updated about 8 hours ago • 4.93k • 242 • 1

liked a model 1 day ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 3 days ago • 1.17M • • 3.77k

replied to witcheer's post 2 days ago

4.8x faster is a lot! Nice results.

reacted to sergiopaniego's post with 🔥 2 days ago

Post

454

OpenEnv already ships 🚢 with a ready-to-deploy RLM environment on free HF Spaces

Drop "Attention Is All You Need", write code that spawns parallel LLM calls → ✅ correct answer, reward 1.0, in 4.2s

Run GRPO (TRL) → model learns to write that search strategy itself

test it yourself → sergiopaniego/repl-env
check out OpenEnv → https://github.com/meta-pytorch/OpenEnv

reacted to Abdourakib's post with 🔥 2 days ago

Post

412

🚀 Just shipped: Visual Analyst Agent

Upload any chart, table, or dashboard screenshot and get instant AI-powered analysis. No API key needed. Free for everyone.

What it does:
→ Detects the visual type automatically
→ Extracts the data into a structured table
→ Writes a plain-English trend analysis
→ Redraws the chart interactively with Plotly
→ Chat with your visual for follow-up questions
→ Export a full HTML report

Built with Python · Streamlit · Google Gemini Vision · Plotly · Pandas

🔗 Try it: huggingface.co/spaces/Abdourakib/visual-analyst-agent
💻 Code: github.com/Abdrakib/visual-analyst-agent

Feedback welcome! 🙏

reacted to evalstate's post with ❤️ 2 days ago

Post

2061

Hugging Face MCP Server v0.3.12
~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The hub_repo_details tool now enables Dataset inspection (view splits, sample rows).

reacted to danielhanchen's post with 🔥 2 days ago

Post

8410

We made a guide on how to run open LLMs in Claude Code, Codex and OpenClaw.

Use Gemma 4 and Qwen3.6 GGUFs for local agentic coding on 24GB RAM

Run with self-healing tool calls, code execution, web search via the Unsloth API endpoint and llama.cpp

Guide: https://unsloth.ai/docs/basics/api

reacted to ArtelTaleb's post with 🔥 3 days ago

Post

2457

✈️ World Flight Arcade - Can you land in 60 seconds?

I just dropped a new browser game built entirely with Three.js: World Flight Arcade

The concept is brutally simple:
- 🕐 60 seconds of flight above a neon wireframe city
- ✈️ One single attempt to land on the runway
- 💀 No second chances. No respawn. Just you, the controls, and the clock.

The camera system is fully dynamic - it stays locked behind the plane within a ±45° pitch/yaw envelope, giving you that cinematic flight feel while keeping full spatial awareness.

Can you nail the landing on your first try?

👉 Play here: ArtelTaleb/world-flight-arcade

Built by Artel3D - handcrafted in Three.js, zero dependencies, runs directly in your browser.

Drop your score in the comments 👇

#gamedev #threejs #browserGame #webgl #artel3d #indiegame

reacted to BlueNipples's post with 👀 3 days ago

Post

2855

Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is.

1 reply

·

reacted to salma-remyx's post with 🔥 3 days ago

Post

3488

VQASynth is the open source implementation of the SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities (2401.12168) paper, putting together the data synthesis pipeline behind remyxai/SpaceQwen2.5-VL-3B-Instruct, remyxai/SpaceThinker-Qwen2.5VL-3B, and several other spatial reasoning models we've shared here on HF.

From early development through production, different categories of evidence become available to guide what to try next. The strongest decisions combine evidence across categories rather than relying on any one.

Stage 1: Development history
Commit history holds the moments where things changed. For VQASynth, that's how scenes get parsed, how captions get generated, how spatial relations get encoded. Even before a model is in production, those milestones are a strong signal for what methods are semantically relevant to where the system is now.

Stage 2: Observational outcomes
Once a model is serving, the same commit history delineates changes against real-world results. That opens up quasi-experiments. You get causal evidence about which changes drove which outcomes, and inference on questions you haven't directly tested.

Stage 3: Controlled experiments
When teams start running interventions, those outcomes tighten the estimates further. This is the regime most people associate with rigor, but it's expensive and gated by traffic.

Stage 4: Counterfactual perturbations
When A/B testing becomes the operational bottleneck, instrumenting decision points in the production system lets you probe what would have happened under alternative choices. Shadow mode first, live traffic once audits pass.

Experimentation maturity is a journey, and every stage offers something to learn from.
More on these ideas: https://docs.remyx.ai/concepts/maturity-progression

reacted to their post with 🚀 3 days ago

Post

3987

Hey Hugging Face!

Repo: https://github.com/unmodeled-tyler/vessel-browser

I wanted to share a cool feature from my open source AI native web browser, Vessel: Persistent highlights!

You can highlight anything on the page and the context is provided to the agent. It's kind of a fun way to learn about new stuff, synthesize info, or just deepen your comprehension/understanding.

Since highlights are persistent, you can close the page, come back later - and your highlights will be exactly where you left them. I've found this particularly useful when reviewing technical blogs, model cards, etc.

Check it out!

1 reply

·

replied to their post 3 days ago

Vessel Browser is BYOK, and supports local models over Ollama/Llama.cpp as well!

posted an update 3 days ago

Post

3987

Hey Hugging Face!

Repo: https://github.com/unmodeled-tyler/vessel-browser

I wanted to share a cool feature from my open source AI native web browser, Vessel: Persistent highlights!

You can highlight anything on the page and the context is provided to the agent. It's kind of a fun way to learn about new stuff, synthesize info, or just deepen your comprehension/understanding.

Since highlights are persistent, you can close the page, come back later - and your highlights will be exactly where you left them. I've found this particularly useful when reviewing technical blogs, model cards, etc.

Check it out!

1 reply

·

reacted to yuriyvnv's post with 🔥 3 days ago

Post

3535

📄 The WAVe paper is officially out in the Information Sciences Journal.

You saw the PT and NL model releases earlier this year. This is the peer-reviewed paper behind them, with the full method, ablations, and downstream ASR evaluation.

Quick recap: WAVe is a 1B multimodal embedding model that filters synthetic speech at the word level, not the sentence level. On Portuguese ASR it cuts training steps by 34%, improves cross-domain generalization by 50%, and matches WER with 30% less synthetic data.

📦 Resources
- Paper: https://www.sciencedirect.com/science/article/pii/S0020025526005220
- PT model: yuriyvnv/WAVe-1B-Multimodal-PT
- NL model: yuriyvnv/WAVe-1B-Multimodal-NL
- Collection: https://huggingface.co/collections/yuriyvnv/multi-modal-embeddings-for-synthetic-transcript-filtering
- Code: https://github.com/yuriyvnv/WAVe

If you train ASR on synthetic or back-translated data, would like to see WAVe benchmarked on other languages.

@reach-vb @ylacombe @hf-audio @BramVanroy

#speech #asr #multimodal #syntheticdata #lowresource

reacted to Crownelius's post with 😎 3 days ago

Post

3900

Day 4-6 [05/05/2026]
Howdy,

Is anybody else willing to put a second mortgage on their house, just to spend 40k USD in compute credits? Just me? k...

I got dreams, man. The datasets I could build with 40k would be insane.
Somebody called me a genius the other day, they'd be shocked to find out, that I would put my house on the line for 30 days of runpod usage.

What would you do with it?
I would turn arxiv into a dataset. Turn each arxiv paper into a QnA.
Or... maybe if I got 40k USD in credit's Id end up like those 16 lost scientists.

Food for thought.
Anyways, I think I'm going to make a post once a week.
In the meantime you can find me building small llm's in discord here:
https://discord.gg/4DdwS9D8x9

6 replies

·

Tyler Williams PRO

AI & ML interests

Recent Activity

Organizations

unmodeled-tyler/DoW-UFO-UAP-1

unmodeled-tyler/DoW-UFO-UAP-1

unmodeled-tyler/DoW-UFO-UAP-1

deepseek-ai/DeepSeek-V4-Pro

Tyler Williams PRO

AI & ML interests

Recent Activity

Organizations

unmodeled-tyler's activity