Ziya-LLaMA-13B-v1

Name: Ziya-LLaMA-13B-v1
Author: IDEA研究院

基础大模型

Ziya-LLaMA-13B-v1

Release date: 2023-05-16更新于: 2023-08-15 18:14:28.618706

Live demo

Ziya-LLaMA-13B-v1 is an AI model published by IDEA研究院, released on 2023-05-16, for 基础大模型, with 130.0B parameters, and 4K tokens context length, requiring about 26 storage, under the 开源不可商用 license.

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

Ziya-LLaMA-13B-v1

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

4K tokens

Max output length

No data

Model type

基础大模型

Release date

2023-05-16

Model file size

MoE architecture

Total params / Active params

13B / N/A

Knowledge cutoff

No data

Ziya-LLaMA-13B-v1

Open source & experience

Code license

Apache 2.0

Weights license

开源不可商用- 不可以商用

GitHub repo

https://github.com/IDEA-CCNL/Fengshenbang-LM

Hugging Face

https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1

Live demo

No live demo

Ziya-LLaMA-13B-v1

Model Overview

姜子牙通用大模型V1是基于LLaMa的130亿参数的大规模预训练模型，具备翻译，编程，文本分类，信息抽取，摘要，文案生成，常识问答和数学计算等能力。目前姜子牙通用大模型已完成大规模预训练、多任务有监督微调和人类反馈学习三阶段的训练过程。

Ziya-LLaMA-13B-v1

Model basics

Open source & experience

Official resources

API details

Benchmark Results

Publisher

Model Overview

Foundation model

DataLearner 官方微信