Llama3.1-70B-Instruct

Name: Llama3.1-70B-Instruct
Author: Facebook AI研究实验室

基础大模型

Release date: 2024-07-23更新于: 2024-07-24 00:00:53580

Live demo

Parameters

700.0亿

Context length

128K

Chinese support

Not supported

Reasoning ability

Llama3.1-70B-Instruct is an AI model published by Facebook AI研究实验室, released on 2024-07-23, for 基础大模型, with 700.0B parameters, and 128K tokens context length, requiring about 140GB storage, under the LLAMA 3.1 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

Llama3.1-70B-Instruct

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

基础大模型

Release date

2024-07-23

Model file size

140GB

MoE architecture

Total params / Active params

700.0B / N/A

Knowledge cutoff

No data

Llama3.1-70B-Instruct

Open source & experience

Code license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT

Weights license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT- 免费商用授权

GitHub repo

https://github.com/meta-llama/llama-models/tree/main/models/llama3_1

Hugging Face

https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct

Live demo

No live demo

Llama3.1-70B-Instruct

API details

API speed

No data

No public API pricing yet.

Llama3.1-70B-Instruct

Benchmark Results

Llama3.1-70B-Instruct currently shows benchmark results led by MBPP (5 / 28, score 86), MMLU (32 / 64, score 86), HumanEval (23 / 39, score 80.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.