Skip to content
Trending storyDeveloping

Hugging Face releases LoRA adapters tuning LFM2.5-24B for agentic harnesses

1 article1 sourcesince Oct 30Last article 1h ago ·

Overview

AISummary of 1 article

Hugging Face released LoRA adapters trained on top of Liquid AI's LFM2.5-24B-A2B model for open-source agentic harnesses, according to a post from Hugging Face's team.

The adapters cover Pi and Claude Code. Hugging Face says they make agentic development more efficient and cut tool calls by up to 40% on Pi.

Liquid AI announced the release on X, saying the Hugging Face team tuned its model for more efficient agentic behavior.

Written by AI from the articles below · updated Oct 30, 1:13 PM ET

Check the sources:

Latest developmentOct 30, 1:06 PM ET
Liquid AI says Hugging Face tuned LFM2.5-24B-A2B for agentic work

Article timeline

The articles in this story. Times are ET.

Oct 30
  1. Liquid AIOfficial
    Liquid AI says Hugging Face tuned LFM2.5-24B-A2B for agentic work

    AILiquid AI says the Hugging Face team tuned its LFM2.5-24B-A2B model for more efficient agentic behavior in open-source harnesses. Hugging Face released LoRA adapters for Pi and Claude Code, which cut tool calls by up to 40% on Pi.

Heat Trend

Not enough continuous observations to show a trend yet.