Compressing LLMs with MoP: Mixture of Pruners Code is available at: https://github.com/c2d-usp/Efficient-LLMs-with-MoP c2d-usp/MoP_llava_1.5_40_percent_compression_2_epochs 4B • Updated Feb 12 c2d-usp/MoP_llava_1.5_30_percent_compression_2_epochs 5B • Updated Feb 12 c2d-usp/MoP_llava_1.5_20_percent_compression_2_epochs 6B • Updated Feb 12 • 12 c2d-usp/MoP_llama_3_40_percent_compression_2_epochs 5B • Updated Feb 12
Efficient Large Language Models Code is available at: https://github.com/c2d-usp/Efficient-LLMs-with-AMP/tree/main c2d-usp/AMP_llama_1_20_percent_compression 5B • Updated Feb 25, 2025 • 1 c2d-usp/AMP_llama_2_30_percent_compression 5B • Updated Feb 25, 2025 • 1 c2d-usp/AMP_phi_1.5_30_percent_compression 1.0B • Updated Feb 25, 2025 • 2 c2d-usp/AMP_phi_2_30_percent_compression 2B • Updated Feb 25, 2025 • 2
Compressing LLMs with MoP: Mixture of Pruners Code is available at: https://github.com/c2d-usp/Efficient-LLMs-with-MoP c2d-usp/MoP_llava_1.5_40_percent_compression_2_epochs 4B • Updated Feb 12 c2d-usp/MoP_llava_1.5_30_percent_compression_2_epochs 5B • Updated Feb 12 c2d-usp/MoP_llava_1.5_20_percent_compression_2_epochs 6B • Updated Feb 12 • 12 c2d-usp/MoP_llama_3_40_percent_compression_2_epochs 5B • Updated Feb 12
Efficient Large Language Models Code is available at: https://github.com/c2d-usp/Efficient-LLMs-with-AMP/tree/main c2d-usp/AMP_llama_1_20_percent_compression 5B • Updated Feb 25, 2025 • 1 c2d-usp/AMP_llama_2_30_percent_compression 5B • Updated Feb 25, 2025 • 1 c2d-usp/AMP_phi_1.5_30_percent_compression 1.0B • Updated Feb 25, 2025 • 2 c2d-usp/AMP_phi_2_30_percent_compression 2B • Updated Feb 25, 2025 • 2
