|
|
| base_model.model.model.embed_tokens.weight torch.Size([32028, 4096]) |
| base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.24.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.24.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.24.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.24.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.24.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.24.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.24.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.24.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.25.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.25.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.25.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.25.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.25.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.25.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.25.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.25.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.26.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.26.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.26.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.26.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.26.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.26.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.26.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.26.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.27.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.27.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.27.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.27.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.27.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.27.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.27.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.27.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.28.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.28.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.28.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.28.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.28.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.28.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.28.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.28.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.29.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.29.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.29.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.29.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.29.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.29.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.29.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.29.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.30.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.30.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.30.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.30.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.30.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.30.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.30.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.30.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.31.self_attn.o_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.31.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.layers.31.mlp.gate_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.31.mlp.gate_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.31.mlp.up_proj.lora_A.default.weight torch.Size([32, 4096]) |
| base_model.model.model.layers.31.mlp.up_proj.lora_B.default.weight torch.Size([11008, 32]) |
| base_model.model.model.layers.31.mlp.down_proj.lora_A.default.weight torch.Size([32, 11008]) |
| base_model.model.model.layers.31.mlp.down_proj.lora_B.default.weight torch.Size([4096, 32]) |
| base_model.model.model.vl_projector.visual_query_tokens torch.Size([1, 32, 768]) |
| base_model.model.model.vl_projector.visual_ln.weight torch.Size([1024]) |
| base_model.model.model.vl_projector.visual_ln.bias torch.Size([1024]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.embeddings.word_embeddings.weight torch.Size([30522, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.embeddings.position_embeddings.weight torch.Size([512, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.embeddings.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.embeddings.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.self.query.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.self.key.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.self.key.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.self.value.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.self.value.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.output.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.self.query.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.self.key.weight torch.Size([768, 1024]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.self.key.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.self.value.weight torch.Size([768, 1024]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.self.value.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.output.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.intermediate.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.intermediate.dense.bias torch.Size([3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.intermediate_query.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.intermediate_query.dense.bias torch.Size([3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output_query.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output_query.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output_query.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.0.output_query.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.self.query.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.self.key.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.self.key.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.self.value.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.self.value.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.output.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.self.query.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.self.key.weight torch.Size([768, 1024]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.self.key.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.self.value.weight torch.Size([768, 1024]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.self.value.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.output.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.intermediate.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.intermediate.dense.bias torch.Size([3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.intermediate_query.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.intermediate_query.dense.bias torch.Size([3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output_query.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output_query.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output_query.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.bert.encoder.layer.1.output_query.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.cls.predictions.bias torch.Size([30522]) |
| base_model.model.model.vl_projector.visual_Qformer.cls.predictions.transform.dense.weight torch.Size([768, 768]) |
| base_model.model.model.vl_projector.visual_Qformer.cls.predictions.transform.dense.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.cls.predictions.transform.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.vl_projector.visual_Qformer.cls.predictions.transform.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.vl_projector.visual_proj.0.weight torch.Size([4096, 768]) |
| base_model.model.model.vl_projector.visual_proj.0.bias torch.Size([4096]) |
| base_model.model.model.vl_projector.visual_proj.2.weight torch.Size([4096, 4096]) |
| base_model.model.model.vl_projector.visual_proj.2.bias torch.Size([4096]) |
| base_model.model.model.al_projector.audio_query_tokens torch.Size([1, 32, 768]) |
| base_model.model.model.al_projector.audio_ln.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_ln.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.embeddings.word_embeddings.weight torch.Size([30522, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.embeddings.position_embeddings.weight torch.Size([512, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.embeddings.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.embeddings.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.self.query.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.self.key.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.self.key.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.self.value.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.self.value.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.output.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.attention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.self.query.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.self.key.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.self.key.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.self.value.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.self.value.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.output.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.crossattention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.intermediate.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.intermediate.dense.bias torch.Size([3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.intermediate_query.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.intermediate_query.dense.bias torch.Size([3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output_query.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output_query.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output_query.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.0.output_query.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.self.query.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.self.key.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.self.key.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.self.value.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.self.value.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.output.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.attention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.self.query.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.self.query.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.self.key.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.self.key.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.self.value.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.self.value.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.output.dense.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.output.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.crossattention.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.intermediate.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.intermediate.dense.bias torch.Size([3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.intermediate_query.dense.weight torch.Size([3072, 768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.intermediate_query.dense.bias torch.Size([3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output_query.dense.weight torch.Size([768, 3072]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output_query.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output_query.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.bert.encoder.layer.1.output_query.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.cls.predictions.bias torch.Size([30522]) |
| base_model.model.model.al_projector.audio_Qformer.cls.predictions.transform.dense.weight torch.Size([768, 768]) |
| base_model.model.model.al_projector.audio_Qformer.cls.predictions.transform.dense.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.cls.predictions.transform.LayerNorm.weight torch.Size([768]) |
| base_model.model.model.al_projector.audio_Qformer.cls.predictions.transform.LayerNorm.bias torch.Size([768]) |
| base_model.model.model.al_projector.audio_proj.0.weight torch.Size([4096, 768]) |
| base_model.model.model.al_projector.audio_proj.0.bias torch.Size([4096]) |
| base_model.model.model.al_projector.audio_proj.2.weight torch.Size([4096, 4096]) |
| base_model.model.model.al_projector.audio_proj.2.bias torch.Size([4096]) |
| base_model.model.lm_head.weight torch.Size([32028, 4096]) |
| trainable_params: 488.648MB |
