Latest AI Insights

Model Evaluations

Model Directory

Model Comparison

Resource Center

Search blog

加载中...

DataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

产品

Leaderboards
模型对比
Datasets

资源

Tutorials
Editorial
Tool directory

关于

关于我们
隐私政策
数据收集方法
联系我们

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

隐私政策服务条款

LLaMA Pro - 8B - AI Model Details and Benchmarks | DataLearnerAI

Page navigation

目录

Model catalogLLaMA Pro - 8B

LL

LLaMA Pro - 8B

LLaMA Pro - 8B

Release date: 2024-01-04更新于: 2024-01-06 22:08:33.412217

Live demoGitHub Hugging Face Compare

Parameters

83.0亿

Context length

4K

Chinese support

Not supported

Reasoning ability

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

LLaMA Pro - 8B

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

4K tokens

Max output length

No data

Model type

LLaMA Pro - 8B

Open source & experience

Code license

Weights license

Llama 2 Community License Agreement- 免费商用授权

GitHub repo

https://github.com/TencentARC/LLaMA-Pro

Hugging Face

https://huggingface.co/TencentARC/LLaMA-Pro-8B

LLaMA Pro - 8B

Official resources

Paper

LLaMA Pro: Progressive LLaMA with Block Expansion

DataLearnerAI blog

No blog post yet

LLaMA Pro - 8B

API details

API speed

No data

No public API pricing yet.

LLaMA Pro - 8B

Benchmark Results

No benchmark data to show.

LLaMA Pro - 8B

Publisher

Tencent ARC

View publisher details

LLaMA Pro - 8B

Model Overview

LLaMA Pro - 8B是腾讯ARC实验室提出的一种大模型微调的方法。相比较传统的有监督微调方法，这个方法可以更好地解决微调的知识遗忘问题。

相比较原始的Llama2-7B，LLaMA Pro - 8B增加了13亿的参数，但是效果好很多：

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送

DataLearner 官方微信二维码

基础大模型

Release date

2024-01-04

Model file size

16.72GB

MoE architecture

No

Total params / Active params

83.0B / N/A

Knowledge cutoff

No data

Live demo

No live demo