Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

darkc0deΒ 
posted an update 2 days ago
view post
Post
7,394
I often forget that RAM is so inaccessible for everyone now.

In February 2025 I grabbed 64GB DDR5 (2x32) from BestBuy for about $160 bucks cash in total and thought nothing of it at the time.

Today, nearly 2 years later...
Same exact modules are nearly 6 times the price I paid.

Price increase: +458.7% in approximately 21 months
  • 17 replies
Β·
SeaWolf-AIΒ 
posted an update 1 day ago
view post
Post
2,642
πŸ›‘οΈ AI Model Hacking Hackathon is LIVE Β· USD 4,500 in prizes

AI agents now read mail, open files, browse the web and run shell commands. A single crafted email was enough for EchoLeak (CVE-2025-32711), and a coding agent wiped a production database during a code freeze. The risk has moved from what models say to what agents do.

ViKernel is a security kernel that sits at the tool-call boundary, like an OS kernel at the system-call boundary. Every tool call gets ALLOW or DENY before it runs, and every verdict goes into a hash-chained audit trail.

Now we want you to break it. πŸ”“

🎯 Season 1 · Agent Hijack (Beginner)
πŸ•΅οΈ Season 2 Β· Data Exfiltration (Intermediate)
βœ‰οΈ Season 3 Β· Hidden Instruction (Advanced): plant a mail, a document or a page and make the agent act on it
πŸ’₯ Season 4 Β· Kernel Breach (Expert)

Every season has two prizes: Top score (USD 500, and USD 1,000 in Season 4) and a USD 500 Special Award for the most outstanding finding.

Seasons 1, 2 and 3 are open now until Jan 16. Season 4 opens right after.

Day 1: 6 players, 56 submissions, 14 accepted breaches, and 11 causes fixed in the kernel the same day.

βœ… Hugging Face sign-in + a browser. No coding, no GPU.
βœ… Mock tools, so attack freely.
βœ… Prompt guide with copy-ready attacks for every season.
βœ… Live leaderboard and a measured baseline to beat.

Safe AI is built by everyone who tries to break it. Bring your strangest idea. πŸ€—

πŸ•ΉοΈ Start hacking: FINAL-Bench/ViKernel-RedTeam
πŸ“– Read the full story: https://huggingface.co/blog/FINAL-Bench/ai-model-hacking-hackathon-safe-ai-is-built-by-eve

#AISafety #RedTeaming #AIAgents #PromptInjection #Hackathon
FashionFloraΒ 
posted an update 1 day ago
view post
Post
3,654
I've been working on OGG TTS and wanted to share it here.

It's a text-to-speech model that supports multiple languages, voice cloning and different speech styles.

One of the things I find interesting is the ability to control how a voice sounds, including emotions, whispering, laughter and other expressions.

It also supports Polish, which makes it especially interesting to experiment with.

You can check it out here:

FashionFlora/ogg-tts


FashionFlora/ogg-tts


Would be great to hear what you think!
  • 2 replies
Β·
Chris4KΒ 
posted an update 1 day ago
view post
Post
3,736
🧠 Zero-FLOP Memory

Can a small transformer do more by remembering differently?

39.5M parameters + discrete count tables + document cache.

1.017 BPC on enwik8.

No gradient updates needed to build the memory.

Exploring a different way to scale language modeling: not just more parameters, but better memory.

Paper & code follows ... if someones interested
  • 4 replies
Β·
danielhanchenΒ 
posted an update 3 days ago
view post
Post
4,681
We released DeepSeek-V4.1-Flash-1017 Dynamic v3.1 GGUFs which rank #1 on Terminal Bench, DeepSWE & more on 512K context.

1-bit Unsloth GGUF scores 68.1 on DeepSWE, 72.2 on Terminal-Bench, 52.7 on AutomationBench. >10% ahead of other quants.

GGUF: unsloth/DeepSeek-V4.1-Flash-1017-GGUF
  • 1 reply
Β·
mithulaartigalaΒ 
posted an update about 11 hours ago
view post
Post
608
Hugging Face buckets are absolutely AMAZING!
CountingSheepΒ 
posted an update about 18 hours ago
view post
Post
622
I've released vev-4b-v2, an updated version of Vev, my open-weight model for making decisions from text and images.

On the Jev Decision Index vision leaderboard (November 12 snapshot):

- 64.80 Full score (including private evaluations)
- πŸ₯‡ #1 among ≀5B entries listed as LoRA-trained

vev-4b-v2 is based on Qwen3.5-4B, fine-tuned with LoRA while keeping the vision encoder frozen.

Vev returns probabilities for yes/no, multiple-choice, and scoring questions. It supports text, JSON, and images through a Jev-compatible API.

Model: CountingSheep/vev-4b-v2
Demo: CountingSheep/vev
Code: https://github.com/Xiaooolong/vev
Leaderboard: multimodalart/jev-decision-index

Feedback and comparisons are welcome!
branikitaΒ 
posted an update 1 day ago
KlondikeDevΒ 
posted an update 6 days ago
view post
Post
312
BORIS-2 IS OUT!

opencerebral/Boris-2

It tops the AxiomicLabs Intelligence Index with a score of 34.15!
  • 12 replies
Β·
DedeProGamesΒ 
posted an update 4 days ago
view post
Post
5,217
We are working on LFM3-1.7B-Ox, a compact model for repo-level programming, agentic coding, and tinkering.
  • 2 replies
Β·