{ "metadata": { "total_size": 478964736 }, "weight_map": { "layers.0.input_layernorm.weight": "model.safetensors", "layers.0.attention_conv.base_kernel": "model.safetensors", "layers.0.attention_conv.kernel_projection.weight": "model.safetensors", "layers.0.attention_conv.kernel_projection.scales": "model.safetensors", "layers.0.attention_conv.kernel_projection.biases": "model.safetensors", "layers.0.self_attn.q_proj.weight": "model.safetensors", "layers.0.self_attn.q_proj.scales": "model.safetensors", "layers.0.self_attn.q_proj.biases": "model.safetensors", "layers.0.self_attn.k_proj.weight": "model.safetensors", "layers.0.self_attn.k_proj.scales": "model.safetensors", "layers.0.self_attn.k_proj.biases": "model.safetensors", "layers.0.self_attn.v_proj.weight": "model.safetensors", "layers.0.self_attn.v_proj.scales": "model.safetensors", "layers.0.self_attn.v_proj.biases": "model.safetensors", "layers.0.self_attn.q_norm.weight": "model.safetensors", "layers.0.self_attn.k_norm.weight": "model.safetensors", "layers.0.self_attn.o_proj.weight": "model.safetensors", "layers.0.self_attn.o_proj.scales": "model.safetensors", "layers.0.self_attn.o_proj.biases": "model.safetensors", "layers.0.post_attention_layernorm.weight": "model.safetensors", "layers.0.mlp_conv.base_kernel": "model.safetensors", "layers.0.mlp_conv.kernel_projection.weight": "model.safetensors", "layers.0.mlp_conv.kernel_projection.scales": "model.safetensors", "layers.0.mlp_conv.kernel_projection.biases": "model.safetensors", "layers.0.mlp.gate_proj.weight": "model.safetensors", "layers.0.mlp.gate_proj.scales": "model.safetensors", "layers.0.mlp.gate_proj.biases": "model.safetensors", "layers.0.mlp.up_proj.weight": "model.safetensors", "layers.0.mlp.up_proj.scales": "model.safetensors", "layers.0.mlp.up_proj.biases": "model.safetensors", "layers.0.mlp.down_proj.weight": "model.safetensors", "layers.0.mlp.down_proj.scales": "model.safetensors", "layers.0.mlp.down_proj.biases": "model.safetensors", "layers.1.input_layernorm.weight": "model.safetensors", "layers.1.attention_conv.base_kernel": "model.safetensors", "layers.1.attention_conv.kernel_projection.weight": "model.safetensors", "layers.1.attention_conv.kernel_projection.scales": "model.safetensors", "layers.1.attention_conv.kernel_projection.biases": "model.safetensors", "layers.1.self_attn.q_proj.weight": "model.safetensors", "layers.1.self_attn.q_proj.scales": "model.safetensors", "layers.1.self_attn.q_proj.biases": "model.safetensors", "layers.1.self_attn.k_proj.weight": "model.safetensors", "layers.1.self_attn.k_proj.scales": "model.safetensors", "layers.1.self_attn.k_proj.biases": "model.safetensors", "layers.1.self_attn.v_proj.weight": "model.safetensors", "layers.1.self_attn.v_proj.scales": "model.safetensors", "layers.1.self_attn.v_proj.biases": "model.safetensors", "layers.1.self_attn.q_norm.weight": "model.safetensors", "layers.1.self_attn.k_norm.weight": "model.safetensors", "layers.1.self_attn.o_proj.weight": "model.safetensors", "layers.1.self_attn.o_proj.scales": "model.safetensors", "layers.1.self_attn.o_proj.biases": "model.safetensors", "layers.1.post_attention_layernorm.weight": "model.safetensors", "layers.1.mlp_conv.base_kernel": "model.safetensors", "layers.1.mlp_conv.kernel_projection.weight": "model.safetensors", "layers.1.mlp_conv.kernel_projection.scales": "model.safetensors", "layers.1.mlp_conv.kernel_projection.biases": "model.safetensors", "layers.1.mlp.gate_proj.weight": "model.safetensors", "layers.1.mlp.gate_proj.scales": "model.safetensors", "layers.1.mlp.gate_proj.biases": "model.safetensors", "layers.1.mlp.up_proj.weight": "model.safetensors", "layers.1.mlp.up_proj.scales": "model.safetensors", "layers.1.mlp.up_proj.biases": "model.safetensors", "layers.1.mlp.down_proj.weight": "model.safetensors", "layers.1.mlp.down_proj.scales": "model.safetensors", "layers.1.mlp.down_proj.biases": "model.safetensors", "layers.2.input_layernorm.weight": "model.safetensors", "layers.2.attention_conv.base_kernel": "model.safetensors", "layers.2.attention_conv.kernel_projection.weight": "model.safetensors", "layers.2.attention_conv.kernel_projection.scales": "model.safetensors", "layers.2.attention_conv.kernel_projection.biases": "model.safetensors", "layers.2.self_attn.q_proj.weight": "model.safetensors", "layers.2.self_attn.q_proj.scales": "model.safetensors", "layers.2.self_attn.q_proj.biases": "model.safetensors", "layers.2.self_attn.k_proj.weight": "model.safetensors", "layers.2.self_attn.k_proj.scales": "model.safetensors", "layers.2.self_attn.k_proj.biases": "model.safetensors", "layers.2.self_attn.v_proj.weight": "model.safetensors", "layers.2.self_attn.v_proj.scales": "model.safetensors", "layers.2.self_attn.v_proj.biases": "model.safetensors", "layers.2.self_attn.q_norm.weight": "model.safetensors", "layers.2.self_attn.k_norm.weight": "model.safetensors", "layers.2.self_attn.o_proj.weight": "model.safetensors", "layers.2.self_attn.o_proj.scales": "model.safetensors", "layers.2.self_attn.o_proj.biases": "model.safetensors", "layers.2.post_attention_layernorm.weight": "model.safetensors", "layers.2.mlp_conv.base_kernel": "model.safetensors", "layers.2.mlp_conv.kernel_projection.weight": "model.safetensors", "layers.2.mlp_conv.kernel_projection.scales": "model.safetensors", "layers.2.mlp_conv.kernel_projection.biases": "model.safetensors", "layers.2.mlp.gate_proj.weight": "model.safetensors", "layers.2.mlp.gate_proj.scales": "model.safetensors", "layers.2.mlp.gate_proj.biases": "model.safetensors", "layers.2.mlp.up_proj.weight": "model.safetensors", "layers.2.mlp.up_proj.scales": "model.safetensors", "layers.2.mlp.up_proj.biases": "model.safetensors", "layers.2.mlp.down_proj.weight": "model.safetensors", "layers.2.mlp.down_proj.scales": "model.safetensors", "layers.2.mlp.down_proj.biases": "model.safetensors", "layers.3.input_layernorm.weight": "model.safetensors", "layers.3.attention_conv.base_kernel": "model.safetensors", "layers.3.attention_conv.kernel_projection.weight": "model.safetensors", "layers.3.attention_conv.kernel_projection.scales": "model.safetensors", "layers.3.attention_conv.kernel_projection.biases": "model.safetensors", "layers.3.self_attn.q_proj.weight": "model.safetensors", "layers.3.self_attn.q_proj.scales": "model.safetensors", "layers.3.self_attn.q_proj.biases": "model.safetensors", "layers.3.self_attn.k_proj.weight": "model.safetensors", "layers.3.self_attn.k_proj.scales": "model.safetensors", "layers.3.self_attn.k_proj.biases": "model.safetensors", "layers.3.self_attn.v_proj.weight": "model.safetensors", "layers.3.self_attn.v_proj.scales": "model.safetensors", "layers.3.self_attn.v_proj.biases": "model.safetensors", "layers.3.self_attn.q_norm.weight": "model.safetensors", "layers.3.self_attn.k_norm.weight": "model.safetensors", "layers.3.self_attn.o_proj.weight": "model.safetensors", "layers.3.self_attn.o_proj.scales": "model.safetensors", "layers.3.self_attn.o_proj.biases": "model.safetensors", "layers.3.post_attention_layernorm.weight": "model.safetensors", "layers.3.mlp_conv.base_kernel": "model.safetensors", "layers.3.mlp_conv.kernel_projection.weight": "model.safetensors", "layers.3.mlp_conv.kernel_projection.scales": "model.safetensors", "layers.3.mlp_conv.kernel_projection.biases": "model.safetensors", "layers.3.mlp.gate_proj.weight": "model.safetensors", "layers.3.mlp.gate_proj.scales": "model.safetensors", "layers.3.mlp.gate_proj.biases": "model.safetensors", "layers.3.mlp.up_proj.weight": "model.safetensors", "layers.3.mlp.up_proj.scales": "model.safetensors", "layers.3.mlp.up_proj.biases": "model.safetensors", "layers.3.mlp.down_proj.weight": "model.safetensors", "layers.3.mlp.down_proj.scales": "model.safetensors", "layers.3.mlp.down_proj.biases": "model.safetensors", "layers.4.input_layernorm.weight": "model.safetensors", "layers.4.attention_conv.base_kernel": "model.safetensors", "layers.4.attention_conv.kernel_projection.weight": "model.safetensors", "layers.4.attention_conv.kernel_projection.scales": "model.safetensors", "layers.4.attention_conv.kernel_projection.biases": "model.safetensors", "layers.4.self_attn.q_proj.weight": "model.safetensors", "layers.4.self_attn.q_proj.scales": "model.safetensors", "layers.4.self_attn.q_proj.biases": "model.safetensors", "layers.4.self_attn.k_proj.weight": "model.safetensors", "layers.4.self_attn.k_proj.scales": "model.safetensors", "layers.4.self_attn.k_proj.biases": "model.safetensors", "layers.4.self_attn.v_proj.weight": "model.safetensors", "layers.4.self_attn.v_proj.scales": "model.safetensors", "layers.4.self_attn.v_proj.biases": "model.safetensors", "layers.4.self_attn.q_norm.weight": "model.safetensors", "layers.4.self_attn.k_norm.weight": "model.safetensors", "layers.4.self_attn.o_proj.weight": "model.safetensors", "layers.4.self_attn.o_proj.scales": "model.safetensors", "layers.4.self_attn.o_proj.biases": "model.safetensors", "layers.4.post_attention_layernorm.weight": "model.safetensors", "layers.4.mlp_conv.base_kernel": "model.safetensors", "layers.4.mlp_conv.kernel_projection.weight": "model.safetensors", "layers.4.mlp_conv.kernel_projection.scales": "model.safetensors", "layers.4.mlp_conv.kernel_projection.biases": "model.safetensors", "layers.4.mlp.gate_proj.weight": "model.safetensors", "layers.4.mlp.gate_proj.scales": "model.safetensors", "layers.4.mlp.gate_proj.biases": "model.safetensors", "layers.4.mlp.up_proj.weight": "model.safetensors", "layers.4.mlp.up_proj.scales": "model.safetensors", "layers.4.mlp.up_proj.biases": "model.safetensors", "layers.4.mlp.down_proj.weight": "model.safetensors", "layers.4.mlp.down_proj.scales": "model.safetensors", "layers.4.mlp.down_proj.biases": "model.safetensors", "layers.5.input_layernorm.weight": "model.safetensors", "layers.5.attention_conv.base_kernel": "model.safetensors", "layers.5.attention_conv.kernel_projection.weight": "model.safetensors", "layers.5.attention_conv.kernel_projection.scales": "model.safetensors", "layers.5.attention_conv.kernel_projection.biases": "model.safetensors", "layers.5.self_attn.q_proj.weight": "model.safetensors", "layers.5.self_attn.q_proj.scales": "model.safetensors", "layers.5.self_attn.q_proj.biases": "model.safetensors", "layers.5.self_attn.k_proj.weight": "model.safetensors", "layers.5.self_attn.k_proj.scales": "model.safetensors", "layers.5.self_attn.k_proj.biases": "model.safetensors", "layers.5.self_attn.v_proj.weight": "model.safetensors", "layers.5.self_attn.v_proj.scales": "model.safetensors", "layers.5.self_attn.v_proj.biases": "model.safetensors", "layers.5.self_attn.q_norm.weight": "model.safetensors", "layers.5.self_attn.k_norm.weight": "model.safetensors", "layers.5.self_attn.o_proj.weight": "model.safetensors", "layers.5.self_attn.o_proj.scales": "model.safetensors", "layers.5.self_attn.o_proj.biases": "model.safetensors", "layers.5.post_attention_layernorm.weight": "model.safetensors", "layers.5.mlp_conv.base_kernel": "model.safetensors", "layers.5.mlp_conv.kernel_projection.weight": "model.safetensors", "layers.5.mlp_conv.kernel_projection.scales": "model.safetensors", "layers.5.mlp_conv.kernel_projection.biases": "model.safetensors", "layers.5.mlp.gate_proj.weight": "model.safetensors", "layers.5.mlp.gate_proj.scales": "model.safetensors", "layers.5.mlp.gate_proj.biases": "model.safetensors", "layers.5.mlp.up_proj.weight": "model.safetensors", "layers.5.mlp.up_proj.scales": "model.safetensors", "layers.5.mlp.up_proj.biases": "model.safetensors", "layers.5.mlp.down_proj.weight": "model.safetensors", "layers.5.mlp.down_proj.scales": "model.safetensors", "layers.5.mlp.down_proj.biases": "model.safetensors", "fc.weight": "model.safetensors", "fc.scales": "model.safetensors", "fc.biases": "model.safetensors", "hidden_norm.weight": "model.safetensors", "norm.weight": "model.safetensors", "candidate_selector.hidden_projection.weight": "model.safetensors", "candidate_selector.hidden_projection.scales": "model.safetensors", "candidate_selector.hidden_projection.biases": "model.safetensors", "candidate_selector.predecessor_codebook": "model.safetensors", "candidate_selector.successor_codebook": "model.safetensors" } }