ERNIE 1.0

Name: Enhanced Representation through kNowledge IntEgration
Author: 百度

基础大模型

Enhanced Representation through kNowledge IntEgration

Release date: 2019-03-16更新于: 2023-07-08 07:28:00.959663

Live demoGitHubHugging FaceCompare

Parameters

3.4亿

Context length

Chinese support

Supported

Reasoning ability

Enhanced Representation through kNowledge IntEgration is an AI model published by 百度, released on 2019-03-16, for 基础大模型, with 3.4B parameters, and 2K tokens context length, under the Apache 2.0 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

ERNIE 1.0

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

基础大模型

Release date

2019-03-16

Model file size

No data

MoE architecture

Total params / Active params

3.4B / N/A

Knowledge cutoff

No data

ERNIE 1.0

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

https://github.com/PaddlePaddle/ERNIE

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

ERNIE 1.0

Official resources

Paper

ERNIE: Enhanced Representation through Knowledge Integration

DataLearnerAI blog

No blog post yet

ERNIE 1.0

API details

API speed

No data

No public API pricing yet.

ERNIE 1.0

Benchmark Results

No benchmark data to show.

ERNIE 1.0

Publisher

百度

View publisher details

Enhanced Representation through kNowledge IntEgration

Model Overview

文心大模型ERNIE是百度发布的产业级知识增强大模型，涵盖了NLP大模型和跨模态大模型。2019年3月，开源了国内首个开源预训练模型文心ERNIE 1.0，此后在语言与跨模态的理解和生成等领域取得一系列技术突破，并对外开源与开放了系列模型，助力大模型研究与产业化应用发展。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送