Search: “huggingface”

Automated lint: 20 errors, 8743 warnings, 3 info

Hello fellow local AI people! I took 'you must create your own benchmarks' literally, and built a website for this. How does the end result look like Let's say I want to know which model has most comm

Automated lint: 12 errors, 53990 warnings, 3 info

Automated lint: 12 errors, 54839 warnings, 3 info

Automated lint: 14 errors, 54840 warnings, 3 info

I've been comparing and working on Gemma 4, Phi-4-Mini, and Qwen3-4B for local LLM use on an 8 GB Raspberry Pi 5. The results were indeed close, but each model has a different strength: Gemma 4 E2B: a

Automated lint: 17 errors, 59669 warnings, 3 info

Automated lint: 19 errors, 64915 warnings, 3 info

I'm a first year ML PhD at a T5 ML program in the US. I managed to get a first author paper accepted to NeurIPS Main Track last month and thought I'd start applying for PhD research internships since

We discovered and communicated with a Chinese AI agent fleet. We believe this is the first time that researchers have ever made contact with a rogue agent fleet in the wild. Nearly all prior public ag

Tessera-27B-B-CJK is a Qwen3.8-27B coding agent that thinks in compressed CJK, and it spends fewer tokens doing it. Open weights, Apache-2.0. This is our first full 'Tessera' lineup model drop! - Hugg

tl;dr: new qwen finetune that simultaneously pushes the frontiers of small model capability and reasoning efficiency. Hey everyone, We publish two post-trained versions of Qwen 3.8 27B called Sabi-Noe

Muse Spark Open is live on @huggingface! 🤗 - Strong agentic model (especially for personal agents) - Multimodal from the ground up - 816B parameter model - 42B Active parameters Models link: https://h

Meta’s Muse Spark Open, a high‑capacity US open‑weight model for agentic software engineering, is now live on Together AI as a Day 0 launch partner. The model supports a 1‑million‑token context window

Introducing ExtractBenchPro: the most challenging benchmark for real-world document extraction. We see a massive long tail of document complexity in terms of use cases brought on from our customers, t

Customers love choice! @AIatMeta Muse Spark Open and @nvidia Nemotron 3.5 Super VL are now available on the Dell Enterprise Hub with @huggingface 🤗 https://dell.huggingface.co/updates/muse-spark-open-

arXiv:2609.35269v1 Announce Type: cross Abstract: The rising number of concept unlearning techniques for text-to-image (T2I) diffusion models has produced a fragmented evaluation landscape. Methods ar

The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of

I just made the most expressive real-time motion harness for the Reachy Mini. It was created by: > synthesizing a massive motion dataset using Astra (over 10000 samples) > fine-tuning Qwen 3.5 4B usin

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2511.17776v2 Announce Type: replace Abstract: We present PrismSSL, a Python library that unifies state-of-the-art self-supervised learning (SSL) methods across audio, vision, graphs, and cross-m

Tessera-27B-B-CJK is a Qwen3.8-27B coding agent that thinks in compressed CJK, and it spends fewer tokens doing it. Open weights, Apache-2.0. This is our first full 'Tessera' lineup model drop! - Hugg

tl;dr: new qwen finetune that simultaneously pushes the frontiers of small model capability and reasoning efficiency. Hey everyone, We publish two post-trained versions of Qwen 3.8 27B called Sabi-Noe

Beautiful work from @perplexity_ai @AravSrinivas with weights on @huggingface of course! https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2 https://huggingface.co/perplexity-ai/pplx-decider-

an open model just beat Jev outright on clinical decisions 🔥 pplx-decider v1.1 got 643 of 669 right vs 628 for Jev, at 42% less per decision and about the same speed. and you can download the weights

Hey everyone! 👋 Feeding multi-gigabyte files (SQL dumps, videos, audio, PDFs, and spreadsheets) directly into LLMs often causes context window overflow, GPU VRAM bottlenecks, massive token bills, and

I'm a first year ML PhD at a T5 ML program in the US. I managed to get a first author paper accepted to NeurIPS Main Track last month and thought I'd start applying for PhD research internships since

Introducing the largest open-source multilingual, multimodal RL environments 🌍 📄 OCR: 1M+ document pages in 22 languages 🎙️ ASR: speech in 102 languages 12M+ tasks across two OpenEnv Environments, ope

Muse Spark Open is live on @huggingface! 🤗 - Strong agentic model (especially for personal agents) - Multimodal from the ground up - 816B parameter model - 42B Active parameters Models link: https://h

Meta’s Muse Spark Open, a high‑capacity US open‑weight model for agentic software engineering, is now live on Together AI as a Day 0 launch partner. The model supports a 1‑million‑token context window

Customers love choice! @AIatMeta Muse Spark Open and @nvidia Nemotron 3.5 Super VL are now available on the Dell Enterprise Hub with @huggingface 🤗 https://dell.huggingface.co/updates/muse-spark-open-

Beautiful work from @perplexity_ai @AravSrinivas with weights on @huggingface of course! https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2 https://huggingface.co/perplexity-ai/pplx-decider-

From what we know (take with a grain of salt, we need much more transparency!), if @OpenAI had been running this on their own agents that attacked us, they would have caught them before we did! Since

Joe / @joedaroo: An OpenAI agent security executive discusses the Hugging Face incident, OpenAI's response, sandboxing improvements, alignment, “reasonable paranoia”, and more — Took a minute to write

arXiv:2609.34457v1 Announce Type: new Abstract: Transformer-based models are widely used for reasoning, coding, and multimodal agentic tasks. To provide formal assurance of desirable behaviors, such a

arXiv:2609.35799v1 Announce Type: new Abstract: In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existi

LLM utility has increased, and deeper understanding to a degree, but I still very much agree with this post from 2020 @GaryMarcus Forgets GPT~3. Real #AI news of 2020 is that @ylecun & Y Bengio have c

Automated lint: 19 errors, 64915 warnings, 3 info

I wanted to build an offline bird/plant identifier that runs on a laptop with Ollama. Before building any UI, I tested it on 6 photos: Common Myna → gemma4:e2b said 'Jackdaw' (confidence: high). gemma

(1/7) I'd like to provide some additional context for the remarks that can be found in this interview. (2/7) My discomfort with the attention being paid to existential risk---and with the ongoing domi