← 최신 프로덕트

We beat Gemini Embedding 2 by training only 16M params (open weights)

Feature Extraction model with 16.4M parameters. Download, explore files and run it on Hugging Face.

huggingface.co 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Gemini can now natively embed video

    github.com

    so I built sub-second video search

    Hacker News438점

  2. Needle

    github.com

    We Distilled Gemini Tool Calling into a 26M Model

    Hacker News776점

  3. Marlin-2B

    huggingface.co

    a tiny VLM to extract structured information from videos

    Hacker News7점

  4. Extending LLM SVG generation beyond pelicans and bicycles

    gally.net

    Inspired by Simon Willison’s pelican-riding-a-bicycle benchmark, I used Claude, Claude Code, and OpenRouter to get SVGs from six models for thirty similar prompts.

    Hacker News16점

  5. Linear RNN/Reservoir hybrid generative model

    raw.githubusercontent.com

    one C file (no deps.)

    Hacker News7점