| base_model.model.model.embed_tokens.weight torch.Size([32000, 4096]) False | |
| base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.0.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.0.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.0.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.0.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.0.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.0.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.1.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.1.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.1.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.1.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.1.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.1.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.1.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.2.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.2.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.2.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.2.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.3.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.3.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.3.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.3.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.4.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.4.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.4.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.4.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.5.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.5.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.5.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.5.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.6.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.6.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.6.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.6.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.7.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.7.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.7.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.7.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.8.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.8.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.8.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.8.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.9.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.9.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.9.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.9.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.10.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.10.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.10.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.10.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.10.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.10.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.10.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.11.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.11.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.11.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.11.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.11.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.11.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.11.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.12.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.12.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.12.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.12.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.12.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.12.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.12.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.13.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.13.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.13.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.13.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.13.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.13.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.13.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.14.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.14.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.14.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.14.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.14.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.14.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.14.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.15.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.15.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.15.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.15.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.15.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.15.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.15.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.16.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.16.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.16.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.16.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.16.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.16.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.16.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.16.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.16.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.17.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.17.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.17.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.17.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.17.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.17.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.17.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.17.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.17.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.18.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.18.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.18.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.18.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.18.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.18.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.18.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.18.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.18.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.19.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.19.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.19.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.19.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.19.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.19.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.19.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.19.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.19.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.20.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.20.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.20.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.20.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.20.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.20.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.20.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.20.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.20.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.21.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.21.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.21.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.21.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.21.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.21.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.21.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.21.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.21.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.22.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.22.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.22.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.22.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.22.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.22.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.22.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.22.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.22.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.23.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.23.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.23.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.23.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.23.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.23.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.23.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.23.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.23.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.24.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.24.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.24.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.24.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.24.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.24.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.24.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.24.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.24.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.24.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.24.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.24.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.24.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.24.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.24.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.24.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.24.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.25.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.25.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.25.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.25.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.25.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.25.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.25.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.25.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.25.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.25.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.25.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.25.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.25.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.25.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.25.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.25.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.25.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.26.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.26.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.26.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.26.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.26.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.26.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.26.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.26.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.26.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.26.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.26.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.26.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.26.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.26.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.26.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.26.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.26.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.27.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.27.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.27.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.27.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.27.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.27.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.27.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.27.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.27.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.27.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.27.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.27.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.27.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.27.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.27.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.27.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.27.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.28.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.28.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.28.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.28.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.28.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.28.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.28.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.28.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.28.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.28.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.28.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.28.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.28.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.28.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.28.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.28.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.28.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.29.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.29.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.29.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.29.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.29.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.29.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.29.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.29.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.29.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.29.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.29.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.29.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.29.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.29.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.29.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.29.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.29.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.30.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.30.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.30.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.30.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.30.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.30.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.30.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.30.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.30.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.30.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.30.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.30.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.30.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.30.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.30.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.30.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.30.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.31.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.31.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.31.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False | |
| base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) True | |
| base_model.model.model.layers.31.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False | |
| base_model.model.model.layers.31.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.31.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.31.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.31.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.31.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.31.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False | |
| base_model.model.model.layers.31.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) True | |
| base_model.model.model.layers.31.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) True | |
| base_model.model.model.layers.31.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False | |
| base_model.model.model.layers.31.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) True | |
| base_model.model.model.layers.31.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) True | |
| base_model.model.model.layers.31.input_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.layers.31.post_attention_layernorm.weight torch.Size([4096]) False | |
| base_model.model.model.norm.weight torch.Size([4096]) False | |
| base_model.model.model.vision_clip_lmm_projector.mlps.0.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.0.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.0.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.0.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.1.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.1.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.1.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.1.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.2.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.2.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.2.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.2.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.3.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.3.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.3.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.3.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.4.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.4.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.4.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.4.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.5.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.5.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.5.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.5.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.6.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.6.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.6.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.6.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.7.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.7.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.7.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.7.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.8.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.8.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.8.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.8.2.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.9.0.weight torch.Size([4096, 1024]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.9.0.bias torch.Size([4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.9.2.weight torch.Size([4096, 4096]) True | |
| base_model.model.model.vision_clip_lmm_projector.mlps.9.2.bias torch.Size([4096]) True | |
| base_model.model.lm_head.weight torch.Size([32000, 4096]) False | |