LA

LaVie

Vision model

LaVie

Release date: 2023-09-26Updated: 2023-12-05 20:02:40.245609
Parameters
3B
Context length
2K
Chinese support
Not supported
Reasoning ability

LaVie is an AI model published by 上海人工智能实验室, released on 2023-09-26, for Vision model, with 3B parameters, and 2K context length, requiring about 10.04GB storage, under the Apache 2.0 license.

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

LaVie

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Vision model
Modality (in / out)
No data
Release date
2023-09-26
Model file size
10.04GB
MoE architecture
No
Total params / Active params
3B / N/A
Knowledge cutoff
No data
LaVie

Open source & experience

Code license
Weights license
Apache 2.0- 免费商用授权
Live demo
No live demo
LaVie

Official resources

LaVie

API details

API speed
No data
No public API pricing yet.
LaVie

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

LaVie

Publisher

上海人工智能实验室
上海人工智能实验室
View publisher details
LaVie

Model Overview

LaVie is an AI model published by 上海人工智能实验室, released on 2023-09-26, for Vision model, with 3B parameters, and 2K context length, requiring about 10.04GB storage, under the Apache 2.0 license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code