Hugging Face

Hugging Face (Twitter) RT @Sentdex: you vs the guy she told you to not worry about

Hugging Face (Twitter) RT @NielsRogge: SAM-3 is out on @huggingface! A big upgrade from SAM-2, and Meta finally added support for text prompts. Here I tried it out on @hazardeden10's magical goal against @Arsenal using the text prompt "Chelsea player" Works pretty well!

Hugging Face (Twitter) RT @ghita__ha: We are very excited to release zerank-2, @ZeroEntropy_AI 's newest reranker model. 🔥 It shows major improvement on the 5 most common RAG failure modes below. Existing rerankers consistently fail on seemingly “simple” tasks: 🔢 Comparing numbers and date: “Biggest deals closed after 04/2024.” 🗄️ Aggregation: “Top 10 objections of customer X?” 🌍 Multilingual: Major pain point, especially non-English to non-English. 🙏 Instruction-Following: “Find the *counterargument* of the claim in the transcript” 🥇 Calibrated scores: You ask "what should I cook for dinner?", and "I am allergic to nuts" scores too low for your threshold. Many rerankers overfit public benchmarks, and don’t generalize to these real issues. zerank-2 outperforms existing rerankers considerably on all of these failure modes, in real production environments. With zerank-2, you get: * 15% improvement vs Cohere rerank 3.5 on Arabic/Hindi (Miraql dataset) * +12% NDCG@10 on... Перейти на оригинальный пост

‌Hugging Face (Twitter) RT @alexandr_wang: Today we are releasing & open-sourcing Segment Anything 3 (SAM 3). It is a state-of-the-art model for image & video segmentation, and builds upon the work of SAM & SAM 2. SAM3 will also power features in Edits, Meta AI, & Facebook Marketplace soon. https://aidemos.meta.com/segment-anything

Hugging Face (Twitter) RT @RedHat_AI: We’re open-sourcing a set of high quality speculator models for Llamas, Qwens, and gpt-oss on Hugging Face. In real workloads, you can expect 1.5 to 2.5x speedups and sometimes more than 4x. Here’s how this fits into the bigger story for speculative decoding. A thread 🧵:

‌Hugging Face (Twitter) stay tuned!

Hugging Face (Twitter) RT @mervenoyann: Meta COOKED 🔥 SAM3 is here, and it supports text input on top of image/video segmentation! > prompt with point/box (visual), negative/positive prompts for refining masks > accepts text prompts (concepts, e.g. red car) ⏯️ > comes with transformers support from day-0! 🤗

‌Hugging Face (Twitter) RT @TechCrunch: Hugging Face CEO says we’re in an ‘LLM bubble,’ not an ‘AI bubble’

‌Hugging Face (Twitter) RT @ClementDelangue: Fascinating results. Can we get more eyes and analysis on the solve logs to try to understand: ? https://twitter.com/mikeknoop/status/1990822341044212126#m

Hugging Face (Twitter) RT @eliebakouch: Kimi K2 thinking is on par with gemini 3 Pro on HLE with tool? Sad that they are not comparing with leading open source model

Hugging Face (Twitter) RT @RulinShao: 🔥Thrilled to introduce DR Tulu-8B, an open long-form Deep Research model that matches OpenAI DR 💪Yes, just 8B! 🚀 The secret? We present Reinforcement Learning with Evolving Rubrics (RLER) for long-form non-verifiable DR tasks! Our rubrics: - co-evolve with the policy model - are grounded on search knowledge 🧵

Hugging Face (Twitter) RT @RisingSayak: The LLM space is blessed to have awesome tech reports that help push the field further exponentially. The diffusion community kinda lacks that a bit. Good folks at @photoroom_app decided to change that by releasing PRX under Apache 2.0 with solid reporting.