zai-org/GLM-5.2
Modelo de geração de texto em alta no Hugging Face — 33.6 mil downloads e 2.0 mil curtidas da comunidade.
Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Modelo de geração de texto em alta no Hugging Face — 33.6 mil downloads e 2.0 mil curtidas da comunidade.
The HIP kernel uses one-instruction asm wrappers and an eight-wave pipeline to outperform AMD's AITER v3 on MI300X. The post MoonMath AI Open-Sources a HIP Attention Kernel for AMD MI300X That Beats AITER v3 on Every Shape and Rounding Mode appeared first on MarkTechPost .
Modelo de geração de texto em alta no Hugging Face — 361 downloads e 61 curtidas da comunidade.
Modelo de visão e linguagem em alta no Hugging Face — 120.0 mil downloads e 1.2 mil curtidas da comunidade.
Hot tubs sit at about 38 to 40 degrees Celsius, warm enough that most people can only soak for about 15 minutes. NVIDIA’s newest AI servers can run their cooling liquid even hotter — up to 45 degrees Celsius, or 113 degrees Fahrenheit. That higher temperature limit is precisely what makes them more energy efficient. […]
In this tutorial, we build a Prefab application that creates interactive dashboards entirely in Python. We design an operations dashboard with reactive state, charts, tables, filters, forms, tabs, and metrics. We generate synthetic pipeline monitoring data and connect it to live UI controls. We then export the app as static HTML and preview it directly inside Google Colab. The post How to Design Python-First Interactive Dashboards with Prefab Reactive UI Components and Static HTML Export appeare...
Tapered language models allocate more parameters to earlier layers and fewer to later layers, improving performance without increasing total parameters or compute costs.
MeshFlow generates triangle meshes directly using equivariant optimal-transport flow matching models with improved inference speed over autoregressive methods.
Learn how Jason Liu uses Codex to preserve context, manage complex projects, and help work continue beyond a single prompt.
A unified open-source framework for discrete text-trigger optimization that standardizes the development and execution of optimization strategies across various domains and applica…
VESFlow is a training-free safety method for flow matching-based text-to-image generation that edits velocity fields to ensure safe output while maintaining prompt integrity.
KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using encoder-decoder architecture with Matryoshka embedding pooling and cross-attention for effici…