Announcing harness adapters for @Alibaba_Qwen Qwen3.8-27B on @opencode harness!
After yesterday's release of the Pi adapter, we now released to the community the OpenCode version, trained on the v2 version, ready to use for local inference.
SWE-Bench Pro (Hard 51 subset) pass@1: 35.3% -> 51.0% | xhigh thinking mode 47.1% -> 54.9%
Terminal Bench 2.1 pass@1: 47.0 -> 53.0 | xhigh thinking mode 55.4 -> 56.6
Generated tokens (content + reas content + tool calls): 6-8x fewer tokens per task !
huggingface.co/harness-hub/Q… 🧵
The AI Podcast is back.
@huggingface's @Thom_Wolf and @ServiceNow's Amanda Grady join us to talk open models, agent safety, and helping more people build with AI.
0:00 AI safety beyond the prompt
1:50 Open and proprietary models for cyber defense
3:28 Giving agents their own identity and permissions
5:07 AI Passport and NVIDIA Sentry
6:03 What better security unlocks
8:32 Open source and security
10:58 Bringing safety into the physical world
13:10 Making fine-tuning more accessible
14:09 What’s next—and why they’re optimistic
Hugging Face retweeted
alzheimer's is a puzzle with missing pieces. we're going to find them 🧩
introducing the MecCog Challenge, a collab between @huggingface and the founders of CASP
let's piece together causal mechanisms of the disease to push the frontier
prizes in HF credits 🤗
Hugging Face retweeted
Today we're open-sourcing HubEgo-100K: the most diverse egocentric dataset on 🤗 @huggingface.
100,000 hours of skilled tasks from 100,000+ different Hub contributors.
Free for research and commercial use 🧵
Hugging Face retweeted
Introducing Qwen3.8-27B-pi-adapted 🤗
We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter.
The results, measured as pass@1:
🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7%
💻 Terminal-Bench 2.1: 39.5% → 55.8%
⚡ 55–62% fewer tool calls per task
This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛
Open weights: huggingface.co/harness-hub/Q…
Methodology: huggingface.co/blog/harness-…
20 million downloads for NVIDIA Cosmos on @HuggingFace! 🎉
To the developers and researchers building robots, autonomous vehicles and vision AI agents with open world models: thank you for experimenting, sharing feedback and building with us.
Tell us what you're building with Cosmos next! 💚
Announcing harness adapters for @Alibaba_Qwen Qwen3.8-27B on Pi harness!
We're releasing a LoRA adapter that makes Qwen3.8-27B a much better and efficient agent behind Pi harness.
SWE-Bench Pro (Hard 51 subset) pass@1: 29% -> 63%
Terminal-Bench 2.1 pass@1: 40% -> 56%
Much more efficient: 55-62% fewer tool calls per task 🤯
huggingface.co/harness-hub/Q…
The era of harness-specific adapters is now on! More harness adapters to come in the next days 🧵
Hugging Face retweeted
An end 2 end fine tuning guide for 3D model just dropped in Hugging Face. 😱
huggingface.co/blog/3d-lora-…
Hugging Face retweeted
i asked claude to implement trellis.2 fully in cuda c++, and it is 5.3x faster than the original pytorch implementation 🚀
surprisingly, the glb-export function was the bottleneck, not the neural net itself. moving exporting to the gpu gave more gains than anything else.
- zero python runtime, all in c++ ⚡️
- cost 💵 ? ~$7 on claude and ~$60 on compute for testing on h200s through @huggingface jobs
- it still gave 2.2x better perf while being bitwise identical 🎯
the code is open-sourced for use here -- github.com/suvadityamuk/trel…
use it as a source for your agent to optimize your models, or utilize it directly. happy hacking! 🤗
Hugging Face retweeted
Too many people treat AI as a zero-sum race. Open-source is winning by doing the opposite: collaboration over competition!
This is why we’re excited to release today the first part of our partnership with @OpenRouter to make open models easier to use for all! Hugging Face for storage and collaboration. OpenRouter for inference. Connected so you can:
🤗 Run OpenRouter inference directly on Hugging Face
🔓 Access Open model weights directly from OpenRouter
🤖 Store your OpenRouter agent traces on HF to inspect them, train better models or share them with the world!
More collaboration. Fewer zero-sum games. More power to AI builders. Let’s build! 💛💛💛
We're teaming up to accelerate open-source Al.
OpenRouter is now integrated into Hugging Face directly. Same token, same endpoint, plus live model stats on the Hub and an inference widget we redesigned together.
The best of open, in one place. huggingface.co/blog/openrout…
Hugging Face retweeted
Over the last few months we optimized the llama.cpp CI to keep up with the fast pace of development
- We now use HF Buckets to store most of our Github Actions cache
- We use HF Jobs to enroll additional CI runners
More info in this blog post:
huggingface.co/blog/ggml-org…
Hugging Face retweeted
Export, quantize and run end-to-end every transformers model, on any backend: same inputs, same outputs, drop-in replacement. 🧵👇
Docs: huggingface.co/docs/transfor…
Release notes: github.com/huggingface/trans…
Hugging Face retweeted
AsyncGRPOTrainer is now stable in TRL v1.18.0!
generation and training run at the same time on separate GPUs, instead of taking turns
we wrote up how to run it, what you can train with it and how it compares with GRPOTrainer: huggingface.co/spaces/trl-li…
Hugging Face retweeted
We’re not going to win by lobbying, plotting, or manipulating. We’re going to win by building, in the open, with the whole community!
Today, with @ggerganov we’re super excited to announce the release of llama.cpp v1, the first major fully stable version of the most used library to run AI models locally, meaning on your phone, your laptop, and your workstation.
It means you can own your intelligence for free, not send your data to anyone and be 100% in control, wherever you are in the world. It shows our commitment to support every hardware, platform and model type out there and makes AI distributed rather than concentrated in a few Silicon Valley orgs.
Huge thanks to the team, the long-time maintainers and every contributor who helped make this happen. Let’s build! 💛🧡💚
llama.cpp v1.0.0 is now available
huggingface.co/blog/ggml-org…
Hugging Face retweeted
today, llama.cpp releases v1 🚀
llama.cpp team commits to keep covering every platform and every model, while keeping the platform robust and lean for everyone that builds on it 🫡
read more about the release here huggingface.co/blog/ggml-org…
Hugging Face retweeted
llama.cpp v1.0.0 is now available
huggingface.co/blog/ggml-org…
Hugging Face retweeted
As promised, we’re releasing Inkling 2 Small’s weights, thanks to the hard work of our team and safety testing partners
Inkling 2 Small’s weights are now available for download on HuggingFace under an Apache 2.0 license.
Make Inkling your own!
huggingface.co/thinkingmachi…
Hugging Face retweeted
Inkling 2 Small’s weights are now available for download on HuggingFace under an Apache 2.0 license.
Make Inkling your own!
huggingface.co/thinkingmachi…





















