--- license: apache-2.0 language: - en - zh library_name: mlx pipeline_tag: text-generation tags: - minicpm - minicpm5 - llama - text-generation - long-context - tool-calling - on-device - edge-ai - heretic - uncensored - decensored - abliterated - mlx datasets: - openbmb/Ultra-FineWeb - openbmb/Ultra-FineWeb-L3 - openbmb/UltraData-Math - openbmb/UltraData-SFT-2605 base_model: dalatexcoder/MiniCPM5-1B-heretic-som --- Quants of [dalatexcoder/MiniCPM5-1B-heretic-som](https://huggingface.co/dalatexcoder/MiniCPM5-1B-heretic-som). 2, 3, 4, 5, 6, 8 bit mixed. [INFO] Quantizing [INFO] Quantized model with 4.306 bits per weight. Output model size: 554.8 MB Done! OptiQ model saved to: ./MiniCPM5-1B-Heretic-MLX-4bit/optiq_mixed Raw Details: Top 20 most-sensitive layers at 2-bit: 1. lm_head sens=4.799e-01 params=200,540,160 2. model.layers.1.self_attn.o_proj sens=2.809e-01 params=3,145,728 3. model.layers.4.mlp.down_proj sens=2.541e-01 params=7,077,888 4. model.layers.1.self_attn.v_proj sens=1.466e-01 params=393,216 5. model.layers.23.mlp.down_proj sens=1.338e-01 params=7,077,888 6. model.layers.0.mlp.down_proj sens=1.199e-01 params=7,077,888 7. model.layers.0.self_attn.o_proj sens=1.155e-01 params=3,145,728 8. model.layers.2.self_attn.v_proj sens=9.771e-02 params=393,216 9. model.layers.4.self_attn.v_proj sens=9.069e-02 params=393,216 10. model.layers.8.self_attn.o_proj sens=8.221e-02 params=3,145,728 11. model.layers.11.self_attn.o_proj sens=8.050e-02 params=3,145,728 12. model.layers.4.mlp.up_proj sens=7.259e-02 params=7,077,888 13. model.layers.1.mlp.down_proj sens=7.142e-02 params=7,077,888 14. model.layers.10.self_attn.o_proj sens=6.905e-02 params=3,145,728 15. model.layers.12.self_attn.o_proj sens=6.872e-02 params=3,145,728 16. model.layers.5.mlp.up_proj sens=6.575e-02 params=7,077,888 17. model.layers.1.self_attn.q_proj sens=6.040e-02 params=3,145,728 18. model.layers.23.mlp.up_proj sens=6.036e-02 params=7,077,888 19. model.layers.6.mlp.up_proj sens=5.986e-02 params=7,077,888 20. model.layers.3.mlp.up_proj sens=5.563e-02 params=7,077,888 Top 20 most-sensitive layers at 3-bit: 1. lm_head sens=1.042e-01 params=200,540,160 2. model.layers.4.mlp.down_proj sens=7.892e-02 params=7,077,888 3. model.layers.1.self_attn.v_proj sens=3.553e-02 params=393,216 4. model.layers.23.mlp.down_proj sens=3.540e-02 params=7,077,888 5. model.layers.1.self_attn.o_proj sens=2.688e-02 params=3,145,728 6. model.layers.2.self_attn.v_proj sens=2.617e-02 params=393,216 7. model.layers.0.mlp.down_proj sens=2.576e-02 params=7,077,888 8. model.layers.0.self_attn.o_proj sens=2.521e-02 params=3,145,728 9. model.layers.8.self_attn.o_proj sens=2.308e-02 params=3,145,728 10. model.layers.11.self_attn.o_proj sens=2.019e-02 params=3,145,728 11. model.layers.10.self_attn.o_proj sens=1.672e-02 params=3,145,728 12. model.layers.12.self_attn.o_proj sens=1.593e-02 params=3,145,728 13. model.layers.5.mlp.up_proj sens=1.564e-02 params=7,077,888 14. model.layers.9.self_attn.o_proj sens=1.542e-02 params=3,145,728 15. model.layers.1.mlp.down_proj sens=1.487e-02 params=7,077,888 16. model.layers.7.mlp.up_proj sens=1.464e-02 params=7,077,888 17. model.layers.2.self_attn.o_proj sens=1.432e-02 params=3,145,728 18. model.layers.3.self_attn.v_proj sens=1.425e-02 params=393,216 19. model.layers.6.mlp.up_proj sens=1.402e-02 params=7,077,888 20. model.layers.0.mlp.up_proj sens=1.391e-02 params=7,077,888 Top 20 most-sensitive layers at 4-bit: 1. lm_head sens=2.590e-02 params=200,540,160 2. model.layers.4.mlp.down_proj sens=1.958e-02 params=7,077,888 3. model.layers.1.self_attn.v_proj sens=1.038e-02 params=393,216 4. model.layers.23.mlp.down_proj sens=9.017e-03 params=7,077,888 5. model.layers.0.mlp.down_proj sens=7.697e-03 params=7,077,888 6. model.layers.1.self_attn.o_proj sens=7.600e-03 params=3,145,728 7. model.layers.2.self_attn.v_proj sens=7.303e-03 params=393,216 8. model.layers.0.self_attn.o_proj sens=7.085e-03 params=3,145,728 9. model.layers.8.self_attn.o_proj sens=5.952e-03 params=3,145,728 10. model.layers.11.self_attn.o_proj sens=5.067e-03 params=3,145,728 11. model.layers.5.mlp.up_proj sens=4.940e-03 params=7,077,888 12. model.layers.1.mlp.down_proj sens=4.700e-03 params=7,077,888 13. model.layers.10.self_attn.o_proj sens=4.471e-03 params=3,145,728 14. model.layers.4.self_attn.v_proj sens=4.441e-03 params=393,216 15. model.layers.3.self_attn.v_proj sens=4.279e-03 params=393,216 16. model.layers.12.self_attn.o_proj sens=4.129e-03 params=3,145,728 17. model.layers.3.mlp.up_proj sens=4.090e-03 params=7,077,888 18. model.layers.1.self_attn.q_proj sens=4.058e-03 params=3,145,728 19. model.layers.6.mlp.up_proj sens=4.025e-03 params=7,077,888 20. model.layers.2.self_attn.o_proj sens=3.845e-03 params=3,145,728 Top 20 most-sensitive layers at 5-bit: 1. lm_head sens=6.904e-03 params=200,540,160 2. model.layers.4.mlp.down_proj sens=4.846e-03 params=7,077,888 3. model.layers.1.self_attn.v_proj sens=3.023e-03 params=393,216 4. model.layers.0.self_attn.o_proj sens=2.795e-03 params=3,145,728 5. model.layers.0.mlp.down_proj sens=2.696e-03 params=7,077,888 6. model.layers.1.self_attn.o_proj sens=2.634e-03 params=3,145,728 7. model.layers.2.self_attn.v_proj sens=2.525e-03 params=393,216 8. model.layers.23.mlp.down_proj sens=2.442e-03 params=7,077,888 9. model.layers.1.mlp.down_proj sens=2.005e-03 params=7,077,888 10. model.layers.8.self_attn.o_proj sens=1.998e-03 params=3,145,728 11. model.layers.3.self_attn.v_proj sens=1.904e-03 params=393,216 12. model.layers.2.self_attn.o_proj sens=1.846e-03 params=3,145,728 13. model.layers.0.self_attn.v_proj sens=1.842e-03 params=393,216 14. model.layers.0.mlp.up_proj sens=1.832e-03 params=7,077,888 15. model.layers.11.self_attn.o_proj sens=1.815e-03 params=3,145,728 16. model.layers.4.mlp.up_proj sens=1.793e-03 params=7,077,888 17. model.layers.4.self_attn.v_proj sens=1.793e-03 params=393,216 18. model.layers.3.mlp.up_proj sens=1.780e-03 params=7,077,888 19. model.layers.3.self_attn.o_proj sens=1.770e-03 params=3,145,728 20. model.layers.1.self_attn.q_proj sens=1.769e-03 params=3,145,728 Top 20 most-sensitive layers at 6-bit: 1. model.layers.4.mlp.down_proj sens=2.093e-03 params=7,077,888 2. lm_head sens=1.755e-03 params=200,540,160 3. model.layers.1.self_attn.v_proj sens=1.749e-03 params=393,216 4. model.layers.0.self_attn.o_proj sens=1.682e-03 params=3,145,728 5. model.layers.0.mlp.down_proj sens=1.621e-03 params=7,077,888 6. model.layers.1.self_attn.o_proj sens=1.507e-03 params=3,145,728 7. model.layers.2.self_attn.v_proj sens=1.497e-03 params=393,216 8. model.layers.1.mlp.down_proj sens=1.370e-03 params=7,077,888 9. model.layers.0.self_attn.v_proj sens=1.366e-03 params=393,216 10. model.layers.0.mlp.up_proj sens=1.356e-03 params=7,077,888 11. model.layers.0.self_attn.k_proj sens=1.326e-03 params=393,216 12. model.layers.0.self_attn.q_proj sens=1.293e-03 params=3,145,728 13. model.layers.1.mlp.up_proj sens=1.293e-03 params=7,077,888 14. model.layers.1.self_attn.q_proj sens=1.292e-03 params=3,145,728 15. model.layers.2.self_attn.o_proj sens=1.278e-03 params=3,145,728 16. model.layers.0.mlp.gate_proj sens=1.273e-03 params=7,077,888 17. model.layers.1.mlp.gate_proj sens=1.259e-03 params=7,077,888 18. model.layers.3.self_attn.v_proj sens=1.251e-03 params=393,216 19. model.layers.2.mlp.up_proj sens=1.241e-03 params=7,077,888 20. model.layers.1.self_attn.k_proj sens=1.234e-03 params=393,216 Top 20 most-sensitive layers at 8-bit: 1. model.layers.0.self_attn.v_proj sens=1.262e-03 params=393,216 2. model.layers.0.self_attn.k_proj sens=1.251e-03 params=393,216 3. model.layers.0.self_attn.o_proj sens=1.249e-03 params=3,145,728 4. model.layers.0.mlp.down_proj sens=1.209e-03 params=7,077,888 5. model.layers.1.self_attn.v_proj sens=1.208e-03 params=393,216 6. model.layers.0.self_attn.q_proj sens=1.207e-03 params=3,145,728 7. model.layers.0.mlp.up_proj sens=1.200e-03 params=7,077,888 8. model.layers.0.mlp.gate_proj sens=1.197e-03 params=7,077,888 9. model.layers.1.self_attn.o_proj sens=1.176e-03 params=3,145,728 10. model.layers.1.self_attn.q_proj sens=1.158e-03 params=3,145,728 11. model.layers.1.mlp.up_proj sens=1.125e-03 params=7,077,888 12. model.layers.1.self_attn.k_proj sens=1.123e-03 params=393,216 13. model.layers.1.mlp.down_proj sens=1.122e-03 params=7,077,888 14. model.layers.1.mlp.gate_proj sens=1.118e-03 params=7,077,888 15. model.layers.2.self_attn.v_proj sens=1.109e-03 params=393,216 16. model.layers.4.mlp.down_proj sens=1.096e-03 params=7,077,888 17. model.layers.2.self_attn.o_proj sens=1.085e-03 params=3,145,728 18. model.layers.2.self_attn.q_proj sens=1.075e-03 params=3,145,728 19. model.layers.2.mlp.down_proj sens=1.074e-03 params=7,077,888 20. model.layers.3.self_attn.o_proj sens=1.072e-03 params=3,145,728