VI

VisCPM-Paint

Multimodal modelVisCPM

VisCPM-Paint

Release date: 2023-06-30Updated: 2023-07-07 23:16:30.540543
Parameters
10B
Context length
2K
Chinese support
Supported
Reasoning ability

VisCPM-Paint is an AI model published by 面壁智能, released on 2023-06-30, for Multimodal model, with 10B parameters, and 2K context length, requiring about 22.7GB storage, under the 通用模型许可协议-来源说明-宣传限制-商业授权 license.

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

VisCPM-Paint

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
No data
Release date
2023-06-30
Model file size
22.7GB
MoE architecture
No
Total params / Active params
10B / N/A
Knowledge cutoff
No data
VisCPM-Paint

Open source & experience

VisCPM-Paint

Official resources

Paper
DataLearnerAI blog
No blog post yet
VisCPM-Paint

API details

API speed
No data
No public API pricing yet.
VisCPM-Paint

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

VisCPM-Paint

Publisher

VisCPM-Paint

Model Overview

VisCPM-Paint is an AI model published by 面壁智能, released on 2023-06-30, for Multimodal model, with 10B parameters, and 2K context length, requiring about 22.7GB storage, under the 通用模型许可协议-来源说明-宣传限制-商业授权 license.

Foundation model

DataLearner on WeChat

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

DataLearner WeChat QR code