Vicuna 13B 16K

Name: Vicuna 13B 16K
Author: LM-SYS

聊天大模型

Vicuna 13B 16K

Release date: 2023-08-03更新于: 2023-08-03 13:49:18.049525

Live demo

Vicuna 13B 16K is an AI model published by LM-SYS, released on 2023-08-03, for 聊天大模型, with 130.0B parameters, and 16K tokens context length, requiring about 26GB 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

Vicuna 13B 16K

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

16K tokens

Max output length

No data

Model type

聊天大模型

Release date

2023-08-03

Model file size

26GB

MoE architecture

Total params / Active params

13B / N/A

Knowledge cutoff

No data

Vicuna 13B 16K

Open source & experience

Code license

Apache 2.0

Weights license

Llama 2 Community License Agreement- 免费商用授权

GitHub repo

https://github.com/lm-sys/FastChat

Hugging Face

https://huggingface.co/lmsys/vicuna-7b-v1.5-16k

Live demo

No live demo

Vicuna 13B 16K

Model Overview

LM-SYS开源的最新的基于LLaMA2微调的16K版本vicuna，支持最高16K上下文输入，参数130亿。

Vicuna 13B 16K

Model basics

Open source & experience

Official resources

API details

Benchmark Results

Publisher

Model Overview

Foundation model

DataLearner 官方微信