| { |
| "script": "kev_merge.py", |
| "script_sha256": "260f41d81bb9901b6991b36869dabe0930611c360ab3c0c1a4d7eb7de9331eed", |
| "rule": "bf16(fp32(W) + (B @ A) * lora_alpha / r), kev-src fe64b127 kev/checkpoint.py:296-312", |
| "lora_r": 16, |
| "lora_alpha": 32, |
| "scale": 2.0, |
| "adapter_sha256": "90e817356246e7f18bfa7ca3d31794cd4fbeb3332a66a84cb51d9ceae925f2b2", |
| "adapter_key_prefix": "base_model.model.", |
| "base_key_prefix": "model.language_model.", |
| "adapted_modules": 248, |
| "applied": 248, |
| "adapted_keys": [ |
| "model.language_model.layers.0.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.0.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.0.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.0.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.0.linear_attn.out_proj.weight", |
| "model.language_model.layers.0.mlp.down_proj.weight", |
| "model.language_model.layers.0.mlp.gate_proj.weight", |
| "model.language_model.layers.0.mlp.up_proj.weight", |
| "model.language_model.layers.1.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.1.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.1.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.1.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.1.linear_attn.out_proj.weight", |
| "model.language_model.layers.1.mlp.down_proj.weight", |
| "model.language_model.layers.1.mlp.gate_proj.weight", |
| "model.language_model.layers.1.mlp.up_proj.weight", |
| "model.language_model.layers.10.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.10.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.10.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.10.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.10.linear_attn.out_proj.weight", |
| "model.language_model.layers.10.mlp.down_proj.weight", |
| "model.language_model.layers.10.mlp.gate_proj.weight", |
| "model.language_model.layers.10.mlp.up_proj.weight", |
| "model.language_model.layers.11.mlp.down_proj.weight", |
| "model.language_model.layers.11.mlp.gate_proj.weight", |
| "model.language_model.layers.11.mlp.up_proj.weight", |
| "model.language_model.layers.11.self_attn.k_proj.weight", |
| "model.language_model.layers.11.self_attn.o_proj.weight", |
| "model.language_model.layers.11.self_attn.q_proj.weight", |
| "model.language_model.layers.11.self_attn.v_proj.weight", |
| "model.language_model.layers.12.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.12.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.12.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.12.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.12.linear_attn.out_proj.weight", |
| "model.language_model.layers.12.mlp.down_proj.weight", |
| "model.language_model.layers.12.mlp.gate_proj.weight", |
| "model.language_model.layers.12.mlp.up_proj.weight", |
| "model.language_model.layers.13.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.13.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.13.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.13.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.13.linear_attn.out_proj.weight", |
| "model.language_model.layers.13.mlp.down_proj.weight", |
| "model.language_model.layers.13.mlp.gate_proj.weight", |
| "model.language_model.layers.13.mlp.up_proj.weight", |
| "model.language_model.layers.14.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.14.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.14.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.14.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.14.linear_attn.out_proj.weight", |
| "model.language_model.layers.14.mlp.down_proj.weight", |
| "model.language_model.layers.14.mlp.gate_proj.weight", |
| "model.language_model.layers.14.mlp.up_proj.weight", |
| "model.language_model.layers.15.mlp.down_proj.weight", |
| "model.language_model.layers.15.mlp.gate_proj.weight", |
| "model.language_model.layers.15.mlp.up_proj.weight", |
| "model.language_model.layers.15.self_attn.k_proj.weight", |
| "model.language_model.layers.15.self_attn.o_proj.weight", |
| "model.language_model.layers.15.self_attn.q_proj.weight", |
| "model.language_model.layers.15.self_attn.v_proj.weight", |
| "model.language_model.layers.16.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.16.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.16.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.16.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.16.linear_attn.out_proj.weight", |
| "model.language_model.layers.16.mlp.down_proj.weight", |
| "model.language_model.layers.16.mlp.gate_proj.weight", |
| "model.language_model.layers.16.mlp.up_proj.weight", |
| "model.language_model.layers.17.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.17.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.17.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.17.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.17.linear_attn.out_proj.weight", |
| "model.language_model.layers.17.mlp.down_proj.weight", |
| "model.language_model.layers.17.mlp.gate_proj.weight", |
| "model.language_model.layers.17.mlp.up_proj.weight", |
| "model.language_model.layers.18.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.18.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.18.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.18.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.18.linear_attn.out_proj.weight", |
| "model.language_model.layers.18.mlp.down_proj.weight", |
| "model.language_model.layers.18.mlp.gate_proj.weight", |
| "model.language_model.layers.18.mlp.up_proj.weight", |
| "model.language_model.layers.19.mlp.down_proj.weight", |
| "model.language_model.layers.19.mlp.gate_proj.weight", |
| "model.language_model.layers.19.mlp.up_proj.weight", |
| "model.language_model.layers.19.self_attn.k_proj.weight", |
| "model.language_model.layers.19.self_attn.o_proj.weight", |
| "model.language_model.layers.19.self_attn.q_proj.weight", |
| "model.language_model.layers.19.self_attn.v_proj.weight", |
| "model.language_model.layers.2.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.2.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.2.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.2.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.2.linear_attn.out_proj.weight", |
| "model.language_model.layers.2.mlp.down_proj.weight", |
| "model.language_model.layers.2.mlp.gate_proj.weight", |
| "model.language_model.layers.2.mlp.up_proj.weight", |
| "model.language_model.layers.20.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.20.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.20.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.20.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.20.linear_attn.out_proj.weight", |
| "model.language_model.layers.20.mlp.down_proj.weight", |
| "model.language_model.layers.20.mlp.gate_proj.weight", |
| "model.language_model.layers.20.mlp.up_proj.weight", |
| "model.language_model.layers.21.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.21.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.21.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.21.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.21.linear_attn.out_proj.weight", |
| "model.language_model.layers.21.mlp.down_proj.weight", |
| "model.language_model.layers.21.mlp.gate_proj.weight", |
| "model.language_model.layers.21.mlp.up_proj.weight", |
| "model.language_model.layers.22.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.22.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.22.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.22.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.22.linear_attn.out_proj.weight", |
| "model.language_model.layers.22.mlp.down_proj.weight", |
| "model.language_model.layers.22.mlp.gate_proj.weight", |
| "model.language_model.layers.22.mlp.up_proj.weight", |
| "model.language_model.layers.23.mlp.down_proj.weight", |
| "model.language_model.layers.23.mlp.gate_proj.weight", |
| "model.language_model.layers.23.mlp.up_proj.weight", |
| "model.language_model.layers.23.self_attn.k_proj.weight", |
| "model.language_model.layers.23.self_attn.o_proj.weight", |
| "model.language_model.layers.23.self_attn.q_proj.weight", |
| "model.language_model.layers.23.self_attn.v_proj.weight", |
| "model.language_model.layers.24.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.24.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.24.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.24.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.24.linear_attn.out_proj.weight", |
| "model.language_model.layers.24.mlp.down_proj.weight", |
| "model.language_model.layers.24.mlp.gate_proj.weight", |
| "model.language_model.layers.24.mlp.up_proj.weight", |
| "model.language_model.layers.25.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.25.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.25.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.25.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.25.linear_attn.out_proj.weight", |
| "model.language_model.layers.25.mlp.down_proj.weight", |
| "model.language_model.layers.25.mlp.gate_proj.weight", |
| "model.language_model.layers.25.mlp.up_proj.weight", |
| "model.language_model.layers.26.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.26.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.26.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.26.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.26.linear_attn.out_proj.weight", |
| "model.language_model.layers.26.mlp.down_proj.weight", |
| "model.language_model.layers.26.mlp.gate_proj.weight", |
| "model.language_model.layers.26.mlp.up_proj.weight", |
| "model.language_model.layers.27.mlp.down_proj.weight", |
| "model.language_model.layers.27.mlp.gate_proj.weight", |
| "model.language_model.layers.27.mlp.up_proj.weight", |
| "model.language_model.layers.27.self_attn.k_proj.weight", |
| "model.language_model.layers.27.self_attn.o_proj.weight", |
| "model.language_model.layers.27.self_attn.q_proj.weight", |
| "model.language_model.layers.27.self_attn.v_proj.weight", |
| "model.language_model.layers.28.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.28.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.28.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.28.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.28.linear_attn.out_proj.weight", |
| "model.language_model.layers.28.mlp.down_proj.weight", |
| "model.language_model.layers.28.mlp.gate_proj.weight", |
| "model.language_model.layers.28.mlp.up_proj.weight", |
| "model.language_model.layers.29.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.29.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.29.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.29.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.29.linear_attn.out_proj.weight", |
| "model.language_model.layers.29.mlp.down_proj.weight", |
| "model.language_model.layers.29.mlp.gate_proj.weight", |
| "model.language_model.layers.29.mlp.up_proj.weight", |
| "model.language_model.layers.3.mlp.down_proj.weight", |
| "model.language_model.layers.3.mlp.gate_proj.weight", |
| "model.language_model.layers.3.mlp.up_proj.weight", |
| "model.language_model.layers.3.self_attn.k_proj.weight", |
| "model.language_model.layers.3.self_attn.o_proj.weight", |
| "model.language_model.layers.3.self_attn.q_proj.weight", |
| "model.language_model.layers.3.self_attn.v_proj.weight", |
| "model.language_model.layers.30.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.30.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.30.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.30.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.30.linear_attn.out_proj.weight", |
| "model.language_model.layers.30.mlp.down_proj.weight", |
| "model.language_model.layers.30.mlp.gate_proj.weight", |
| "model.language_model.layers.30.mlp.up_proj.weight", |
| "model.language_model.layers.31.mlp.down_proj.weight", |
| "model.language_model.layers.31.mlp.gate_proj.weight", |
| "model.language_model.layers.31.mlp.up_proj.weight", |
| "model.language_model.layers.31.self_attn.k_proj.weight", |
| "model.language_model.layers.31.self_attn.o_proj.weight", |
| "model.language_model.layers.31.self_attn.q_proj.weight", |
| "model.language_model.layers.31.self_attn.v_proj.weight", |
| "model.language_model.layers.4.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.4.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.4.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.4.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.4.linear_attn.out_proj.weight", |
| "model.language_model.layers.4.mlp.down_proj.weight", |
| "model.language_model.layers.4.mlp.gate_proj.weight", |
| "model.language_model.layers.4.mlp.up_proj.weight", |
| "model.language_model.layers.5.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.5.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.5.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.5.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.5.linear_attn.out_proj.weight", |
| "model.language_model.layers.5.mlp.down_proj.weight", |
| "model.language_model.layers.5.mlp.gate_proj.weight", |
| "model.language_model.layers.5.mlp.up_proj.weight", |
| "model.language_model.layers.6.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.6.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.6.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.6.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.6.linear_attn.out_proj.weight", |
| "model.language_model.layers.6.mlp.down_proj.weight", |
| "model.language_model.layers.6.mlp.gate_proj.weight", |
| "model.language_model.layers.6.mlp.up_proj.weight", |
| "model.language_model.layers.7.mlp.down_proj.weight", |
| "model.language_model.layers.7.mlp.gate_proj.weight", |
| "model.language_model.layers.7.mlp.up_proj.weight", |
| "model.language_model.layers.7.self_attn.k_proj.weight", |
| "model.language_model.layers.7.self_attn.o_proj.weight", |
| "model.language_model.layers.7.self_attn.q_proj.weight", |
| "model.language_model.layers.7.self_attn.v_proj.weight", |
| "model.language_model.layers.8.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.8.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.8.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.8.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.8.linear_attn.out_proj.weight", |
| "model.language_model.layers.8.mlp.down_proj.weight", |
| "model.language_model.layers.8.mlp.gate_proj.weight", |
| "model.language_model.layers.8.mlp.up_proj.weight", |
| "model.language_model.layers.9.linear_attn.in_proj_a.weight", |
| "model.language_model.layers.9.linear_attn.in_proj_b.weight", |
| "model.language_model.layers.9.linear_attn.in_proj_qkv.weight", |
| "model.language_model.layers.9.linear_attn.in_proj_z.weight", |
| "model.language_model.layers.9.linear_attn.out_proj.weight", |
| "model.language_model.layers.9.mlp.down_proj.weight", |
| "model.language_model.layers.9.mlp.gate_proj.weight", |
| "model.language_model.layers.9.mlp.up_proj.weight" |
| ], |
| "dropped_tensors": [ |
| "mtp.fc.weight", |
| "mtp.layers.0.input_layernorm.weight", |
| "mtp.layers.0.mlp.down_proj.weight", |
| "mtp.layers.0.mlp.gate_proj.weight", |
| "mtp.layers.0.mlp.up_proj.weight", |
| "mtp.layers.0.post_attention_layernorm.weight", |
| "mtp.layers.0.self_attn.k_norm.weight", |
| "mtp.layers.0.self_attn.k_proj.weight", |
| "mtp.layers.0.self_attn.o_proj.weight", |
| "mtp.layers.0.self_attn.q_norm.weight", |
| "mtp.layers.0.self_attn.q_proj.weight", |
| "mtp.layers.0.self_attn.v_proj.weight", |
| "mtp.norm.weight", |
| "mtp.pre_fc_norm_embedding.weight", |
| "mtp.pre_fc_norm_hidden.weight" |
| ], |
| "dropped_rule": "mtp.* (unused by Kev's text backbone)", |
| "output_tensors": 723, |
| "output_total_bytes": 9078538752, |
| "shards": { |
| "model.safetensors-00001-of-00002.safetensors": "2a42e56697b0f3928b2466f2f113bc612b248744dc8fc25b732e4d9f3dde2f62", |
| "model.safetensors-00002-of-00002.safetensors": "7d61934b02762a24a7d7209933837094243d0b9c72dd7d2e5393b873d006f9e0" |
| } |
| } |
|
|
