Decision Models + Hugging Face = ❤️
New tag on HF: "decision-model" so you can filter for them and maybe combine with MLX or GGUF to go 100% local? That’s the future 🔥
Already 1,300+ models available.
Show more
Mistral 4 on Hugging Face soon 🤯
decision models + local ai = ❤️
tried Laya (421M) on llama.cpp in a little apple-picking benchmark, it's almost as good as Qwen 4B at 12x the speed.
who wants privacy? then like their answer I guess
@victormustar Nothing to announce yet, but the more people ask, the more likely it gets!
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.
- Frontier reasoning efficiency
- Advances the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch
Full weights release this month.
Learn more about Beam:
Show more
I'm super excited to introduce security-one: our open-weight model for security decisions.
Designed to:
✅ Run 24/7
✅ Assess signals across apps, agents and infra
✅ Return structured probabilities to guide routing
✅ Route suspicious events to stronger models/humans
Show more
This is hugeeee for open-source RL environments.
You can now discover environments across OpenEnv, Verifiers, Harbor, NeMo Gym, and more, all on the @huggingface Hub.
A common home for RL environments is long overdue.
Excited for what’s coming next !
Show more
Say hi to our new @LeRobotHF intern !
(and to my very relative teleop skills)
LTX 2.5 😀 Restore IC-LoRA
it takes archive video (low-resolution web rips, low-bitrate broadcast transfers, tape, sepia or black-and-white film scans) as its reference and renders the same shot as a clean, colour
Show more
Introducing Decision 2.0: our newest state-of-the-art decision models, open in every size from 0.6B to 27B ⚡
HF collection 🤗:
#OpenSource# #Decision# #Jev# #LLM#
Show more
Small bird, fast wings, Kolibri is here.
78B parameters. 3.46B active. Up to 1M tokens of context. Built in Europe.
Now the weights are yours. Run it on your own hardware, under Apache 2.0.
Show more
1/ Excited to release The ultimate guide to multi-harness RL
The same model behaves differently in every agent harness. So we built an open way to train any model with RL on any task set, inside the harnesses people actually use, like Claude Code, Codex, and OpenCode, without changing a single line of harness or training code.
Trained across four harnesses, LFM2.5-2.6B went from 42% to 54% with 31% fewer tool calls. 🧵
Show more
Introducing AstaBrief 8B, an open model that turns complex research questions + literature excerpts into cited reports.
Run it locally on your own hardware, with open weights + training data you can inspect & build on. 🧵
🤗 Download:
Show more
Decision models in llama.cpp are now available
The `/v1/systemone` endpoint is available in the latest llama builds. Use it to do Jev-style inference locally, efficiently and privately. Multiple open models are supported with more to come.
Show more
llama.cpp now supports decision models 🚦
Route tickets, moderate content, or pick an agent's next step: ask typed questions, get a probability for every option.
already 5 open models supported, from 144M to 27B:
Show more
actually you can
OpenAI launched dots. Here's how to build your own dots-style assistants with:
> Pi as the harness
> Custom gateway to connect to Telegram
> Your choice of models (local, open, etc).
> Google Workspace skills
Run them on a VPS, Desktop, DGX, etc. Have fun!!
Show more
Introducing MC-EgoHands, the first all-in-one harness for turning raw ego video into training-ready data.
→ Frontier hand pose (<7mm) across 4 public benchmarks
→ Human grasps retargeted to Panda/LIBERO and Yam in one pass
→ Occluded frames flagged as interpolated or missing
→ Structured episodes in @huggingface @LeRobotHF v3
Show more
Kev 1.0: an open weight family of decision models you can train and run on your own.
• New Kev-27B + updated Kev-9B
• 64k-token document window on Kev-27B
• TypeSafe SDK compatible
• New fine-tuning + deployment skills so you can train Kev on your own data
Show more
Alert (again): Perplexity also just dropped a Jev alternative on Hugging Face 🚨
