← Latest products

Homi

open decision model for audio, near Flash on MMSU and 50x cheaper. Open model that answers typed questions about audio, with a probability for every option. Weights - https://huggingface.co/egma-ai/homi.

Open source

8 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. OpenMeters

    github.com

    A fast and free audio metering/visualization suite

    Hacker News16 pts

  2. T0

    github.com

    We trained a 256M SOTA open-weights time-series forecasting model

    Hacker News14 pts

  3. Open-source model and scorecard for measuring hallucinations in LLMs

    vectara.com

    This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems.

    Hacker News65 pts

  4. Ergonomically call LLM in bulk from CLI

    github.com

    Chorus is a tool for calling an OpenAI-compatible text generation API, in bulk, from the command line, ergonomically.

    Hacker News7 pts

  5. Gutsy

    github.com

    Tiny model for typed decisions on CPU (Jev style)

    Hacker News9 pts