DataLearner logo
SA

SAM

Foundation model

Segment Anything Model

Release date: 2023-04-05Updated: 2023-04-06Views: 1,124
Live demoGitHubHugging FaceCompare
Parameters
1B
Context length
2K
Multilingual
No data
Reasoning ability
No data

Segment Anything Model is an AI model published by Facebook AI Research Lab, released on 2023-04-05, for Foundation model, with 1B parameters, and 2K context length, requiring about 2.4GB storage.

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

SAM

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Foundation model
Modality (in / out)
No data
Release date
2023-04-05
Model file size
2.4GB
MoE architecture
No
Total params / Active params
1B / Not applicable
Knowledge cutoff
No data
SAM

Open source & experience

Code license
No data
Weights license
No data
GitHub repo
N/A
Hugging Face
N/A
Live demo
N/A
SAM

Official resources

Paper
DataLearnerAI blog
N/A
SAM

API details

API speed
No data
No public API pricing yet.
SAM

Publisher

Facebook AI Research Lab
Facebook AI Research Lab
View publisher details
Segment Anything Model

Model Overview

Segment Anything Model is an AI model published by Facebook AI Research Lab, released on 2023-04-05, for Foundation model, with 1B parameters, and 2K context length, requiring about 2.4GB storage.

DataLearner on WeChat

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

DataLearner WeChat QR code