What is Qwen 1.5 MoE?

Qwen1.5-MoE-A2.7B is a small mixture-of-expert (MoE) model with only 2.7 billion activated parameters yet matches the performance of state-of-the-art 7B models like Mistral 7B and Qwen1.5-7B.

Do you use Qwen 1.5 MoE?

Recent Qwen 1.5 MoE Launches

Qwen 1.5 MoE Highly efficient mixture-of-expert (MoE) model from Alibaba

Launched on April 3rd, 2024

Qwen 1.5 MoE Alternatives

Airtrain.ai LLM Playground

3 reviews

Data analysis tools

LLM Explorer

0 reviews

AI Coding Assistants

Review Qwen 1.5 MoE?

Maker reviews of Qwen 1.5 MoE

Salman Paracha

used this to build Arch

Arch

(289 points)

Highly performant base models that can be used for task-specific training. Such as the function calling experience built into Arch

Share

Report

4mo ago