A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever
Paper • 2607.23806 • Published • 7
i come in peace
akirathegreatest
·
AI & ML interests
None yet
Recent Activity
reacted to kasbsquall's post with 🔥 about 2 months ago
🔎 UX Crime Scene — every interface hides a crime.
Drop a screenshot of ANY website or app, and THE INSPECTOR — a film-noir detective — works it as a crime scene: he circles each UX flaw on the real pixels, names the charge, and files a verdict with a letter grade. A UX audit that plays like a detective thriller.
But the verdict is just the opening statement. Now it goes further:
⚖️ THE TRIAL — put the interface on trial. The guilty UI elements take the stand and defend themselves while the Inspector rules from the evidence.
🖼️ THE RECONSTRUCTION — one click and FLUX.2 Klein rebuilds the worst element FIXED, live. Before/after, on the real pixels.
🔊 THE VOICE — hear the verdict read aloud (Kokoro, local, no keys).
🚨 MOST WANTED — a public rogues' gallery. Book your case onto a shared board where the city's worst interfaces are ranked by their crimes. Booked by the public.
Three small models, all on Modal (scale-to-zero), none over 32B:
👁️ Qwen2.5-VL-7B (vision agent) · 🖼️ FLUX.2 Klein (reconstruction) · 🔊 Kokoro-82M (voice)
📊 Human-graded: 84% grounding / 92% valid charges.
▶️ Trailer: https://youtu.be/6u58YIEPrkA
📹 Full walkthrough: https://youtu.be/WyQbY0XJ_9E
🕵️ Try it: https://huggingface.co/spaces/build-small-hackathon/ux-crime-scene
Built solo for #BuildSmallHackathon (Gradio × Hugging Face). Open the case — the Inspector is waiting. reacted to sergiopaniego's post with 🔥 8 months ago
ICYMI, you can fine-tune open LLMs using Claude Code
just tell it:
“Fine-tune Qwen3-0.6B on open-r1/codeforces-cots”
and Claude submits a real training job on HF GPUs using TRL.
it handles everything:
> dataset validation
> GPU selection
> training + Trackio monitoring
> job submission + cost estimation
when it’s done, your model is on the Hub, ready to use
read more about the process: https://huggingface.co/blog/hf-skills-trainingOrganizations
None yet
upvoted a paper 4 days ago
reacted to kasbsquall's post with 🔥 about 2 months ago
Post
4188
🔎 UX Crime Scene — every interface hides a crime.
Drop a screenshot of ANY website or app, and THE INSPECTOR — a film-noir detective — works it as a crime scene: he circles each UX flaw on the real pixels, names the charge, and files a verdict with a letter grade. A UX audit that plays like a detective thriller.
But the verdict is just the opening statement. Now it goes further:
⚖️ THE TRIAL — put the interface on trial. The guilty UI elements take the stand and defend themselves while the Inspector rules from the evidence.
🖼️ THE RECONSTRUCTION — one click and FLUX.2 Klein rebuilds the worst element FIXED, live. Before/after, on the real pixels.
🔊 THE VOICE — hear the verdict read aloud (Kokoro, local, no keys).
🚨 MOST WANTED — a public rogues' gallery. Book your case onto a shared board where the city's worst interfaces are ranked by their crimes. Booked by the public.
Three small models, all on Modal (scale-to-zero), none over 32B:
👁️ Qwen2.5-VL-7B (vision agent) · 🖼️ FLUX.2 Klein (reconstruction) · 🔊 Kokoro-82M (voice)
📊 Human-graded: 84% grounding / 92% valid charges.
▶️ Trailer: https://youtu.be/6u58YIEPrkA
📹 Full walkthrough: https://youtu.be/WyQbY0XJ_9E
🕵️ Try it: build-small-hackathon/ux-crime-scene
Built solo for #BuildSmallHackathon (Gradio × Hugging Face). Open the case — the Inspector is waiting.
Drop a screenshot of ANY website or app, and THE INSPECTOR — a film-noir detective — works it as a crime scene: he circles each UX flaw on the real pixels, names the charge, and files a verdict with a letter grade. A UX audit that plays like a detective thriller.
But the verdict is just the opening statement. Now it goes further:
⚖️ THE TRIAL — put the interface on trial. The guilty UI elements take the stand and defend themselves while the Inspector rules from the evidence.
🖼️ THE RECONSTRUCTION — one click and FLUX.2 Klein rebuilds the worst element FIXED, live. Before/after, on the real pixels.
🔊 THE VOICE — hear the verdict read aloud (Kokoro, local, no keys).
🚨 MOST WANTED — a public rogues' gallery. Book your case onto a shared board where the city's worst interfaces are ranked by their crimes. Booked by the public.
Three small models, all on Modal (scale-to-zero), none over 32B:
👁️ Qwen2.5-VL-7B (vision agent) · 🖼️ FLUX.2 Klein (reconstruction) · 🔊 Kokoro-82M (voice)
📊 Human-graded: 84% grounding / 92% valid charges.
▶️ Trailer: https://youtu.be/6u58YIEPrkA
📹 Full walkthrough: https://youtu.be/WyQbY0XJ_9E
🕵️ Try it: build-small-hackathon/ux-crime-scene
Built solo for #BuildSmallHackathon (Gradio × Hugging Face). Open the case — the Inspector is waiting.
- 1 reply
reacted to sergiopaniego's post with 🔥 8 months ago
Post
2900
ICYMI, you can fine-tune open LLMs using Claude Code
just tell it:
“Fine-tune Qwen3-0.6B on open-r1/codeforces-cots”
and Claude submits a real training job on HF GPUs using TRL.
it handles everything:
> dataset validation
> GPU selection
> training + Trackio monitoring
> job submission + cost estimation
when it’s done, your model is on the Hub, ready to use
read more about the process: https://huggingface.co/blog/hf-skills-training
just tell it:
“Fine-tune Qwen3-0.6B on open-r1/codeforces-cots”
and Claude submits a real training job on HF GPUs using TRL.
it handles everything:
> dataset validation
> GPU selection
> training + Trackio monitoring
> job submission + cost estimation
when it’s done, your model is on the Hub, ready to use
read more about the process: https://huggingface.co/blog/hf-skills-training
- 1 reply
liked 2
models 8 months ago
liked 3
models about 1 year ago
liked a
Space over 1 year ago
upvoted an article over 1 year ago
Article
Mastering Long Contexts in LLMs with KVPress
nvidia
• • 75 liked a
Space about 2 years ago