Qwen-1.5-2.7B

The 'Qwen-1.5-2.7B' is a benchmark used to evaluate the performance and accuracy of simplified Mixture-of-Experts large language models (MoE-LLMs) in comparison to state-of-the-art pruning methods.

Papers using Qwen-1.5-2.7B (1)

MoEITS: A Green AI approach for simplifying MoE-LLMs2026