Llama3-400B-InTraining

Name: Llama3-400B-InTraining
Author: Facebook AI研究实验室

基础大模型

Release date: 2024-04-18更新于: 2024-04-19 00:43:24370

Live demo

Llama3-400B-InTraining is an AI model published by Facebook AI研究实验室, released on 2024-04-18, for 基础大模型, with 4000.0B parameters, and 8K tokens context length, requiring about 800GB storage, under the Llama 2 Community License Agreement license.

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

Llama3-400B-InTraining

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

8K tokens

Max output length

No data

Model type

基础大模型

Release date

2024-04-18

Model file size

800GB

MoE architecture

Total params / Active params

4000.0B / N/A

Knowledge cutoff

No data

Llama3-400B-InTraining

Open source & experience

Code license

Llama 2 Community License Agreement

Weights license

Llama 2 Community License Agreement- 免费商用授权

GitHub repo

https://github.com/meta-llama/llama3

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

Llama3-400B-InTraining

Model Overview

这是MetaAI开源的第三代Llama3模型最大的版本，4000亿参数，在2024年4月18日首次宣布存在，截止当时，还在训练中。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送

Llama3-400B-InTraining

Model basics

Open source & experience

Official resources

API details

Benchmark Results

Publisher

Model Overview

DataLearner 官方微信