Skip to content
Trending storyDeveloping

XingChen-AGI releases Xing4.0-29B-Intent, a 29B model for structured request parsing

1 article1 sourcesince Oct 19Last article 57m ago ·

Overview

AISummary of 1 article

XingChen-AGI releases Xing4.0-29B-Intent, a 29B model that turns one-line requests into structured intent, entities, relations and action parameters, with output constrained to a schema in JSON. The authors report a score of 58 on their extraction evaluation of 6,000 samples drawn from 48 public datasets, ahead of 18 general-purpose models. ModelScope announced the release on X.

Model weights, training data and code are released under the Apache 2.0 license.

Written by AI from the articles below · updated Oct 19, 7:18 AM ET

Check the sources:

Latest developmentOct 19, 7:12 AM ET
Xing4.0-29B-Intent parses requests into structured intent and entities

Article timeline

The articles in this story. Times are ET.

Oct 19
  1. ModelScopeOfficial
    Xing4.0-29B-Intent parses requests into structured intent and entities

    AIXingChen-AGI releases Xing4.0-29B-Intent, a 29B model that turns one-line requests into structured intent, entities, relations, and action parameters. The authors report a score of 58 on their extraction evaluation across 6,000 samples from 48 public datasets, ahead of 18 general-purpose models. The model outputs schema-constrained JSON, and its weights, training data, and code are released under Apache 2.0.

    Image from @ModelScope2022's post

Heat Trend

Not enough continuous observations to show a trend yet.