Llama 2 13B

'LLaMA-2-13B' is a large language model benchmark used to evaluate the performance and capabilities of various compression methods for large language models.

Papers using Llama 2 13B (3)

SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression2026 · 15 citesGPTailor: Large Language Model Pruning Through Layer Cutting and Stitching2025GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching2025