Qwen-2.5

The 'Qwen-2.5' dataset/benchmark is used to evaluate the performance of large language models, specifically in the context of applying synergistic sparse and low-rank compression methods.

Papers using Qwen-2.5 (6)

Fast Multi-dimensional Refusal Subspaces via RFM-AGOP20261+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models2025UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs2025PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters2025TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning2025Bridging the LLM Accessibility Divide? Performance, Fairness, and Cost of Closed versus Open LLMs for Automated Essay Scoring2025