← Latest products

A 150M model that extracts verbatim evidence spans for RAG

no LLM call. Token Classification model with 0.1B parameters. Download, explore files and run it on Hugging Face.

Visit huggingface.coexternal site

Reactions (1)

Similar products

by description similarity

  1. A 0.3B model that redacts PII in all 24 EU languages offline

    huggingface.co

    Token Classification model with 0.3B parameters. Download, explore files and run it on Hugging Face.

    Hacker News6 pts

  2. A lightweight LLM proxy to get structured results from most LLMs

    l1m.io

    After struggling with complex prompt engineering and unreliable parsing, we built L1M, a simple API that lets you extract structured data from unstructured text and images.

    Hacker News13 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. I built a tiny LLM to demystify how language models work

    github.com

    A ~9M parameter LLM that talks like a small fish.

    Hacker News915 pts

  5. Raman-01

    huggingface.co

    A Pocket Physics Solver LLM

    Hacker News5 pts