Skip to content
Trending storyDeveloping

ModelScope releases Phocinae-Largha-150M-v1, a 144.3M bilingual model for local agent decisions

1 article1 sourcesince Oct 9Last article 2h ago ·

Overview

AISummary of 1 article

ModelScope releases Phocinae-Largha-150M-v1, a 144.3M-parameter bilingual model under Apache 2.0, which answers yes/no, pick-one, and 2–10 scoring questions in a single forward pass without generating tokens.

ModelScope reports 0.906 accuracy on its fitted English typed-decisions evaluation and 0.848 on its in-mix Chinese evaluation. At a 0.6 confidence threshold, the model's escalation router cuts LLM calls by 55% while keeping 0.9936 accuracy on the high-confidence subset, according to ModelScope's post on X.

These figures are ModelScope's own results and have not been independently verified.

Written by AI from the articles below · updated Oct 9, 11:45 PM ET

Check the sources:

Latest developmentOct 9, 11:29 PM ET
Phocinae-Largha-150M-v1 handles routine agent decisions locally with no generation tokens

Article timeline

The articles in this story. Times are ET.

Oct 9
  1. ModelScopeOfficial
    Phocinae-Largha-150M-v1 handles routine agent decisions locally with no generation tokens

    AIModelScope releases Phocinae-Largha-150M-v1, a 144.3M-parameter bilingual model under Apache 2.0 that answers yes/no, pick-one, and 2–10 scoring questions in a single forward pass. The model scores 0.906 on the fitted English typed-decisions evaluation and 0.848 on the in-mix Chinese evaluation. At a 0.6 confidence threshold, its escalation router cuts LLM calls by 55% while keeping 0.9936 accuracy on the high-confidence subset.

    Image from @ModelScope2022's post

Heat trend

Not enough continuous observations to show a trend yet.