{ "metadata": { "total_size": 33504330240 }, "weight_map": { "block_chunks.0.module.0.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.0.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.1.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.2.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.3.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.0.module.4.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.0.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.1.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.2.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.3.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ada_gss": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.sa.scale_mul_1H11": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.sa.q_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.sa.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.sa.mat_qkv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.sa.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.sa.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca.v_bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca.mat_q.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca.mat_q.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca.mat_kv.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca.proj.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca.proj.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ffn.fc1.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ffn.fc1.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ffn.fc2.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ffn.fc2.bias": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca_norm.weight": "model-00001-of-00004.safetensors", "block_chunks.1.module.4.ca_norm.bias": "model-00001-of-00004.safetensors", "block_chunks.2.module.0.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.0.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.1.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.2.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.3.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.2.module.4.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.0.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.1.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.2.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.3.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ada_gss": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.sa.scale_mul_1H11": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.sa.q_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.sa.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.sa.mat_qkv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.sa.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.sa.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca.v_bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca.mat_q.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca.mat_q.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca.mat_kv.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca.proj.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca.proj.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ffn.fc1.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ffn.fc1.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ffn.fc2.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ffn.fc2.bias": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca_norm.weight": "model-00002-of-00004.safetensors", "block_chunks.3.module.4.ca_norm.bias": "model-00002-of-00004.safetensors", "block_chunks.4.module.0.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.0.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.1.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.2.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.3.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.4.module.4.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.0.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.1.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.2.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.3.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ada_gss": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.sa.scale_mul_1H11": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.sa.q_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.sa.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.sa.mat_qkv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.sa.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.sa.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca.v_bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca.mat_q.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca.mat_q.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca.mat_kv.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca.proj.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca.proj.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ffn.fc1.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ffn.fc1.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ffn.fc2.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ffn.fc2.bias": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca_norm.weight": "model-00003-of-00004.safetensors", "block_chunks.5.module.4.ca_norm.bias": "model-00003-of-00004.safetensors", "block_chunks.6.module.0.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ada_gss": "model-00004-of-00004.safetensors", "text_norm.weight": "model-00004-of-00004.safetensors", "text_proj_for_sos.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.0.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.1.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.2.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.3.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.4.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.5.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.zero_k_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.0.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.1.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.2.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.3.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.6.module.4.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.0.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.1.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.2.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.3.ca_norm.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ada_gss": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.scale_mul_1H11": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.q_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.mat_qkv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.sa.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.v_bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.mat_q.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.mat_q.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.proj.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca.proj.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ffn.fc1.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ffn.fc1.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ffn.fc2.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ffn.fc2.bias": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca_norm.weight": "model-00004-of-00004.safetensors", "block_chunks.7.module.4.ca_norm.bias": "model-00004-of-00004.safetensors", "text_proj_for_sos.ca.mat_q": "model-00004-of-00004.safetensors", "text_proj_for_sos.ca.v_bias": "model-00004-of-00004.safetensors", "text_proj_for_sos.ca.mat_kv.weight": "model-00004-of-00004.safetensors", "text_proj_for_sos.ca.proj.weight": "model-00004-of-00004.safetensors", "text_proj_for_sos.ca.proj.bias": "model-00004-of-00004.safetensors", "text_proj_for_ca.0.weight": "model-00004-of-00004.safetensors", "text_proj_for_ca.0.bias": "model-00004-of-00004.safetensors", "text_proj_for_ca.2.weight": "model-00004-of-00004.safetensors", "text_proj_for_ca.2.bias": "model-00004-of-00004.safetensors", "lvl_embed.weight": "model-00004-of-00004.safetensors", "word_embed.weight": "model-00004-of-00004.safetensors", "word_embed.bias": "model-00004-of-00004.safetensors", "shared_ada_lin.1.weight": "model-00004-of-00004.safetensors", "shared_ada_lin.1.bias": "model-00004-of-00004.safetensors", "head_nm.ada_lin.1.weight": "model-00004-of-00004.safetensors", "head_nm.ada_lin.1.bias": "model-00004-of-00004.safetensors", "head.weight": "model-00004-of-00004.safetensors", "head.bias": "model-00004-of-00004.safetensors", "cfg_uncond": "model-00004-of-00004.safetensors", "pos_start": "model-00004-of-00004.safetensors" } }