DataLearner logo
M6

M6

Foundation model

Multi-Modality to Multi-Modality Multitask Mega-transformer

Release date: 2021-03-01Updated: 2023-04-05Views: 616
Live demoGitHubHugging FaceCompare
Parameters
100B
Context length
2K
Multilingual
No data
Reasoning ability
No data

Multi-Modality to Multi-Modality Multitask Mega-transformer is an AI model published by Tencent AI Lab, released on 2021-03-01, for Foundation model, with 100B parameters, and 2K context length.

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

M6

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
2021-03-01
Model file size
No data
MoE architecture
No
Total params / Active params
100B / Not applicable
Knowledge cutoff
No data
M6

Open source & experience

Code license
No data
Weights license
No data
GitHub repo
N/A
Hugging Face
N/A
Live demo
N/A
M6

Official resources

Paper
DataLearnerAI blog
N/A
M6

API details

API speed
No data
No public API pricing yet.
M6

Publisher

Multi-Modality to Multi-Modality Multitask Mega-transformer

Model Overview

Multi-Modality to Multi-Modality Multitask Mega-transformer is an AI model published by Tencent AI Lab, released on 2021-03-01, for Foundation model, with 100B parameters, and 2K context length.

DataLearner on WeChat

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

DataLearner WeChat QR code