Experimental News Clipping Site

Tag: transformers

  • Simon Willison’s Weblog: Load Llama-3.2 WebGPU in your browser from a local folder

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/8/webgpu-local-folder/#atom-everything Source: Simon Willison’s Weblog Title: Load Llama-3.2 WebGPU in your browser from a local folder Feedly Summary: Load Llama-3.2 WebGPU in your browser from a local folder Inspired by a comment on Hacker News I decided to see if it was possible to modify the transformers.js-examples/tree/main/llama-3.2-webgpu Llama 3.2 chat demo (online here,…

  • Simon Willison’s Weblog: Introducing EmbeddingGemma

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Sep/4/embedding-gemma/#atom-everything Source: Simon Willison’s Weblog Title: Introducing EmbeddingGemma Feedly Summary: Introducing EmbeddingGemma Brand new open weights (under the slightly janky Gemma license) 308M parameter embedding model from Google: Based on the Gemma 3 architecture, EmbeddingGemma is trained on 100+ languages and is small enough to run on less than 200MB of RAM with…

  • Simon Willison’s Weblog: Introducing Gemma 3 270M: The compact model for hyper-efficient AI

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Aug/14/gemma-3-270m/#atom-everything Source: Simon Willison’s Weblog Title: Introducing Gemma 3 270M: The compact model for hyper-efficient AI Feedly Summary: Introducing Gemma 3 270M: The compact model for hyper-efficient AI New from Google: Gemma 3 270M, a compact, 270-million parameter model designed from the ground up for task-specific fine-tuning with strong instruction-following and text structuring…

  • Cloud Blog: The Dataproc advantage: Advanced Spark features that will transform your analytics and AI

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/data-analytics/why-use-dataproc-for-your-apache-spark-environment/ Source: Cloud Blog Title: The Dataproc advantage: Advanced Spark features that will transform your analytics and AI Feedly Summary: With its exceptional price-performance, Google Cloud’s Dataproc has evolved from a simple, managed open-source software (OSS) service to a powerhouse in Apache Spark and open lakehouses, driving the analytics and AI workloads of…

  • The Register: Boffins detail new algorithms to losslessly boost AI perf by up to 2.8x

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/07/17/new_algorithms_boost_ai_perf/ Source: The Register Title: Boffins detail new algorithms to losslessly boost AI perf by up to 2.8x Feedly Summary: New spin on speculative decoding works with any model – now built into Transformers We all know that AI is expensive, but a new set of algorithms developed by researchers at the Weizmann…

  • Cloud Blog: Introducing BigQuery ObjectRef: Supercharge your multimodal data and AI processing

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/data-analytics/new-objectref-data-type-brings-unstructured-data-into-bigquery/ Source: Cloud Blog Title: Introducing BigQuery ObjectRef: Supercharge your multimodal data and AI processing Feedly Summary: Traditional data warehouses simply can’t keep up with today’s analytics workloads. That’s because today, most data that’s generated is both unstructured and multimodal (documents, audio files, images, and videos). With the complexity of cleaning and transforming…

  • Simon Willison’s Weblog: AbsenceBench: Language Models Can’t Tell What’s Missing

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jun/20/absencebench/#atom-everything Source: Simon Willison’s Weblog Title: AbsenceBench: Language Models Can’t Tell What’s Missing Feedly Summary: AbsenceBench: Language Models Can’t Tell What’s Missing Here’s another interesting result to file under the “jagged frontier" of LLMs, where their strengths and weaknesses are often unintuitive. Long context models have been getting increasingly good at passing "Needle…