Qwen/Qwen1.5-MoE-A2.7B

Text Generation·Qwen· 212.0K· 227

transformers other Text Generation 14.3B params license:otherregion:us

Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data.

# pull & run locally
pip install mlforge-sdk && mlforge pull Qwen/Qwen1.5-MoE-A2.7B

Model details

Task

Text Generation

Provider

Qwen

Framework

transformers

Parameters

14.3B

Size

27 GB

License

other

Downloads

212.0K

Likes

227

Updated

2024-04-18

Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data.