Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

DedeProGamesย 
posted an update 2 days ago
view post
Post
4,888
We are working on LFM3-1.7B-Ox, a compact model for repo-level programming, agentic coding, and tinkering.
  • 2 replies
ยท
Banaxi-Techย 
posted an update 2 days ago
view post
Post
6,235
BananaMind 3 is coming.

Biggest context in all SLMs with NSA.
10M, 50M, 150M, 400M.

And maybe, 1B.
  • 14 replies
ยท
juiceb0xc0deย 
posted an update 3 days ago
view post
Post
3,472
๐Ÿฆ™ llama.cpp hit v1.0.0, so I built it a party

juiceb0xc0de/BYOGGUF: Bring Your Own GGUF. Paste any public model repo, pick a quant, and chat with it on an RTX PRO 6000 Blackwell through ZeroGPU, on the minutes your account already has (5 a day free, 40 on PRO).

If you donโ€™t have a GGUF, the Space will make you one. Sign in, point it at any public safetensors or GGUF repo, pick your quant types, and it converts and quantizes on CPU, so it costs you no GPU quota. The finished quants land in your own account with a model card, and one button takes them straight into the chat room. Something the size of Qwen3.8-27B is fine.

Anything up to 48 GB runs on half the card at the normal rate; bigger models get the full 96 GB and burn minutes twice as fast. Public, ungated repos only. Native CUDA 13 binaries for Blackwell, built on the first stable llama.cpp.
  • 1 reply
ยท
darkc0deย 
posted an update about 12 hours ago
view post
Post
1,478
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
  • 6 replies
ยท
Banaxi-Techย 
posted an update 1 day ago
view post
Post
3,948
We're introducing KV1 1.2B.
Its our first KV1 model using a 2 bit KV cache, based on LFM 2.5 1.2B.

KV1 1.2B retains 75.8% of original intelligence.

More details: klein-ml/blog

Model klein-ml/KV1-1.2B
  • 3 replies
ยท
SeaWolf-AIย 
posted an update 3 days ago
view post
Post
6,532
๐ŸŒฆ๏ธ Which weather model is most accurate? We score them every day, in the open.

We released two things on Hugging Face:

๐Ÿ† Global Weather Model Leaderboard
Every day it records what each global model predicted for 24 world cities, compares it with what actually happened (ERA5), and updates the ranking. ECMWF IFS and AIFS, NOAA GFS and AIGFS, DWD ICON, JMA, ECCC GEM, MET Norway, side by side, on the same cases, since 1 January 2026.

Four elements, four tabs: max temperature, min temperature, wind, precipitation. Forecast leads from 1 to 7 days, with 8 to 10 days joining as they are verified.

๐Ÿงฌ Darwin-Prediction-Weather
VIDRAFT's weather prediction system: a fusion engine that combines global forecasts, learning only from days already observed. It holds the lowest error in all four elements at every lead on the 2026 record, and the lowest error in all 15 evaluated cells of the WeatherBench 2 (2020) protocol.

What the 2026 record shows so far:
โ€ข AI models now lead physics models at the major centres (AIFS vs IFS, AIGFS vs GFS)
โ€ข Fusion goes further: 7-day max temperature RMSE 2.09 ยฐC vs 2.41 ยฐC for the next model

Also inside: yesterday's results with a daily WIN for the closest model, a 10-day outlook for every city, champions by city and by month, and a Live Earth map with wind, clouds, radar and temperature.

Every forecast and every observed value is open as CSV, so anyone can check the scores.

๐Ÿ“– Article: https://huggingface.co/blog/FINAL-Bench/which-weather-model-is-most-accurate-we-score-them
๐Ÿ† Leaderboard: FINAL-Bench/Weather-Model-Leaderboard
๐Ÿงฌ Model: FINAL-Bench/Darwin-Prediction-Weather
๐Ÿ“Š Daily record: FINAL-Bench/Weather-Model-Forecast-Archive

Questions, corrections and new models to add are welcome.
KlondikeDevย 
posted an update 4 days ago
view post
Post
183
BORIS-2 IS OUT!

opencerebral/Boris-2

It tops the AxiomicLabs Intelligence Index with a score of 34.15!
  • 9 replies
ยท
danielhanchenย 
posted an update 1 day ago
view post
Post
365
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
BibbyResearchย 
posted an update 2 days ago
view post
Post
3,677
Have you tried the New Notebook feature on Bibby AI?

I highly recommend for all the researchers - https://trybibby.com/

Featured in the top 10 tools of all time. ๐Ÿ˜Ž๐Ÿ†
  • 1 reply
ยท
sriram1983007ย 
posted an update 1 day ago
view post
Post
831
Should an AI agent sign this payment?

Iโ€™ve released SRA-RiskGate-4B v2. Itโ€™s a 4B model fine-tuned from Qwen3-4B-Instruct that answers approve, hold or reject for stablecoin payments made by agents (x402, EIP-3009, Circle), and it settles payment disputes.

On 2,000 held-out benchmark cases:
โœ… 99.6% of payment decisions correct (base model: 59.8%)
โœ… 0.35% unsafe approvals (base model: 34.6%)
โœ… 90.2% of dispute outcomes correct, up from 77.8% in v1

The main change in v2: the dispute window is computed in code and passed into the prompt instead of asking a 4B model to subtract dates. Wrongful denials fell from 26% to 2.1%.

I also tested it on 227 real USDC payments from Base mainnet: it blocked none of the 151 real payments and approved none of the risky ones.

The model isnโ€™t the security boundary. The open-source checks in pip install sra-riskgate run first and fail closed, with optional Chainalysis, TRM, Range and Webacy screening.

These are my own numbers. Every prediction is public, so you can re-score them.

๐Ÿค– Model: hf.co/sriram1983007/SRA-RiskGate-4B
๐ŸŽฎ Try to trick it: hf.co/spaces/sriram1983007/sra-riskgate-demo
๐Ÿ“Š Benchmark: hf.co/datasets/sriram1983007/sra-stablecoin-risk-bench
๐Ÿงพ Real payments: hf.co/datasets/sriram1983007/sra-real