| { |
| "metadata": { |
| "total_size": 84660491264, |
| "total_parameters": 104186907648 |
| }, |
| "weight_map": { |
| "lm_head.biases": "model-00017-of-00017.safetensors", |
| "lm_head.scales": "model-00017-of-00017.safetensors", |
| "lm_head.weight": "model-00017-of-00017.safetensors", |
| "model.layers.0.attention.dense.biases": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.dense.scales": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.dense.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.g_norm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.g_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.g_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.g_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.key_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.query_key_value.biases": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.query_key_value.scales": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.query_key_value.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.attention.query_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.down_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.down_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.up_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.up_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.dense.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.dense.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.dense.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.g_norm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.g_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.g_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.g_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.key_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.query_key_value.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.query_key_value.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.query_key_value.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.attention.query_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.gate.expert_bias": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.gate.gate_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.gate.gate_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.gate.gate_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.down_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.down_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.gate_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.gate_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.up_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.up_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.10.attention.dense.biases": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.dense.scales": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.dense.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.g_norm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.g_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.g_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.g_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.key_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.query_key_value.biases": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.query_key_value.scales": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.query_key_value.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.attention.query_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.gate.expert_bias": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.gate.gate_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.gate.gate_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.gate.gate_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.dense.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.dense.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.dense.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.g_norm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.g_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.g_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.g_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.key_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.query_key_value.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.query_key_value.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.query_key_value.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.attention.query_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.gate.expert_bias": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.gate.gate_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.gate.gate_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.gate.gate_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.dense.biases": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.dense.scales": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.dense.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.g_norm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.g_proj.biases": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.g_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.g_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.key_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.query_key_value.biases": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.query_key_value.scales": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.query_key_value.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.attention.query_layernorm.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.gate.expert_bias": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.gate.gate_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.gate.gate_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.gate.gate_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.dense.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.dense.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.dense.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.g_norm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.g_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.g_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.g_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.key_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.query_key_value.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.query_key_value.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.query_key_value.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.attention.query_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.gate.expert_bias": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.gate.gate_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.gate.gate_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.gate.gate_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.dense.biases": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.dense.scales": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.dense.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.g_norm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.g_proj.biases": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.g_proj.scales": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.g_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.key_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.query_key_value.biases": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.query_key_value.scales": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.query_key_value.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.attention.query_layernorm.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.gate.expert_bias": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.gate.gate_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.gate.gate_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.gate.gate_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.dense.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.dense.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.dense.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.embed_q.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.embed_q.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.embed_q.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.kv_a_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.kv_a_proj_with_mqa.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.kv_a_proj_with_mqa.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.kv_a_proj_with_mqa.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_a_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_a_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_a_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_a_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_b_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_b_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.q_b_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.unembed_out.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.unembed_out.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.attention.unembed_out.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.gate.expert_bias": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.gate.gate_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.gate.gate_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.gate.gate_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.dense.biases": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.dense.scales": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.dense.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.g_norm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.g_proj.biases": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.g_proj.scales": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.g_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.key_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.query_key_value.biases": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.query_key_value.scales": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.query_key_value.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.attention.query_layernorm.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.gate.expert_bias": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.gate.gate_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.gate.gate_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.gate.gate_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.dense.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.dense.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.dense.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.g_norm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.g_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.g_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.g_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.key_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.query_key_value.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.query_key_value.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.query_key_value.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.attention.query_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.gate.expert_bias": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.gate.gate_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.gate.gate_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.gate.gate_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.dense.biases": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.dense.scales": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.dense.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.g_norm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.g_proj.biases": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.g_proj.scales": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.g_proj.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.key_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.query_key_value.biases": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.query_key_value.scales": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.query_key_value.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.attention.query_layernorm.weight": "model-00009-of-00017.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.gate.expert_bias": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.gate.gate_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.gate.gate_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.gate.gate_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.dense.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.dense.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.dense.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.g_norm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.g_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.g_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.g_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.key_layernorm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.query_key_value.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.query_key_value.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.query_key_value.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.attention.query_layernorm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.gate.expert_bias": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.gate.gate_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.gate.gate_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.gate.gate_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00010-of-00017.safetensors", |
| "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00010-of-00017.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00017.safetensors", |
| "model.layers.2.attention.dense.biases": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.dense.scales": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.dense.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.g_norm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.g_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.g_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.g_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.key_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.query_key_value.biases": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.query_key_value.scales": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.query_key_value.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.attention.query_layernorm.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.gate.expert_bias": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.gate.gate_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.gate.gate_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.gate.gate_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00001-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00001-of-00017.safetensors", |
| "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00001-of-00017.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.20.attention.dense.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.dense.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.dense.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.g_norm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.g_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.g_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.g_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.key_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.attention.query_key_value.biases": "model-00010-of-00017.safetensors", |
| "model.layers.20.attention.query_key_value.scales": "model-00010-of-00017.safetensors", |
| "model.layers.20.attention.query_key_value.weight": "model-00010-of-00017.safetensors", |
| "model.layers.20.attention.query_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.gate.expert_bias": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.gate.gate_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.gate.gate_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.gate.gate_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.dense.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.dense.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.dense.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.g_norm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.g_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.g_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.g_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.key_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.query_key_value.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.query_key_value.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.query_key_value.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.attention.query_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.gate.expert_bias": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.gate.gate_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.gate.gate_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.gate.gate_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00011-of-00017.safetensors", |
| "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00011-of-00017.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00017.safetensors", |
| "model.layers.22.attention.dense.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.dense.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.dense.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.g_norm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.g_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.g_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.g_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.key_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.query_key_value.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.query_key_value.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.query_key_value.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.attention.query_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.gate.expert_bias": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.gate.gate_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.gate.gate_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.gate.gate_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.dense.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.dense.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.dense.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.embed_q.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.embed_q.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.embed_q.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.kv_a_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.kv_a_proj_with_mqa.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.kv_a_proj_with_mqa.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.kv_a_proj_with_mqa.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_a_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_a_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_a_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_a_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_b_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_b_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.q_b_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.unembed_out.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.unembed_out.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.attention.unembed_out.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.gate.expert_bias": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.gate.gate_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.gate.gate_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.gate.gate_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00012-of-00017.safetensors", |
| "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00012-of-00017.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00017.safetensors", |
| "model.layers.24.attention.dense.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.dense.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.dense.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.g_norm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.g_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.g_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.g_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.key_layernorm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.query_key_value.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.query_key_value.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.query_key_value.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.attention.query_layernorm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.input_layernorm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.gate.expert_bias": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.gate.gate_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.gate.gate_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.gate.gate_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.dense.biases": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.dense.scales": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.dense.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.g_norm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.g_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.g_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.g_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.key_layernorm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.query_key_value.biases": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.query_key_value.scales": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.query_key_value.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.attention.query_layernorm.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.input_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.gate.expert_bias": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.gate.gate_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.gate.gate_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.gate.gate_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00013-of-00017.safetensors", |
| "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00013-of-00017.safetensors", |
| "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.dense.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.dense.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.dense.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.g_norm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.g_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.g_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.g_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.key_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.query_key_value.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.query_key_value.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.query_key_value.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.attention.query_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.input_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.gate.expert_bias": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.gate.gate_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.gate.gate_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.gate.gate_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.dense.biases": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.dense.scales": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.dense.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.g_norm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.g_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.g_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.g_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.key_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.query_key_value.biases": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.query_key_value.scales": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.query_key_value.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.attention.query_layernorm.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.input_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.gate.expert_bias": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.gate.gate_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.gate.gate_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.gate.gate_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00014-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00014-of-00017.safetensors", |
| "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00014-of-00017.safetensors", |
| "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.dense.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.dense.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.dense.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.g_norm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.g_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.g_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.g_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.key_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.query_key_value.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.query_key_value.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.query_key_value.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.attention.query_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.input_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.gate.expert_bias": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.gate.gate_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.gate.gate_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.gate.gate_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.dense.biases": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.dense.scales": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.dense.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.g_norm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.g_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.g_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.g_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.key_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.query_key_value.biases": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.query_key_value.scales": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.query_key_value.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.attention.query_layernorm.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.input_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.gate.expert_bias": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.gate.gate_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.gate.gate_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.gate.gate_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00015-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00015-of-00017.safetensors", |
| "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00015-of-00017.safetensors", |
| "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.3.attention.dense.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.dense.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.dense.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.g_norm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.g_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.g_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.g_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.key_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.query_key_value.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.query_key_value.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.query_key_value.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.attention.query_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.gate.expert_bias": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.gate.gate_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.gate.gate_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.gate.gate_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.30.attention.dense.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.dense.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.dense.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.g_norm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.g_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.g_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.g_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.key_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.query_key_value.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.query_key_value.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.query_key_value.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.attention.query_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.input_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.gate.expert_bias": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.gate.gate_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.gate.gate_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.gate.gate_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.dense.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.dense.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.dense.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.embed_q.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.embed_q.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.embed_q.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.kv_a_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.kv_a_proj_with_mqa.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.kv_a_proj_with_mqa.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.kv_a_proj_with_mqa.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_a_layernorm.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_a_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_a_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_a_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_b_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_b_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.q_b_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.unembed_out.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.unembed_out.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.attention.unembed_out.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.input_layernorm.weight": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.gate.expert_bias": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.gate.gate_proj.biases": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.gate.gate_proj.scales": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.gate.gate_proj.weight": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00017-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00016-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00016-of-00017.safetensors", |
| "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00016-of-00017.safetensors", |
| "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00017.safetensors", |
| "model.layers.4.attention.dense.biases": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.dense.scales": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.dense.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.g_norm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.g_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.g_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.g_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.key_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.query_key_value.biases": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.query_key_value.scales": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.query_key_value.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.attention.query_layernorm.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.gate.expert_bias": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.gate.gate_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.gate.gate_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.gate.gate_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00002-of-00017.safetensors", |
| "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00002-of-00017.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.dense.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.dense.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.dense.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.g_norm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.g_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.g_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.g_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.key_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.query_key_value.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.query_key_value.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.query_key_value.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.attention.query_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.gate.expert_bias": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.gate.gate_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.gate.gate_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.gate.gate_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.dense.biases": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.dense.scales": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.dense.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.g_norm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.g_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.g_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.g_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.key_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.query_key_value.biases": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.query_key_value.scales": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.query_key_value.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.attention.query_layernorm.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.gate.expert_bias": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.gate.gate_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.gate.gate_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.gate.gate_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00003-of-00017.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.dense.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.dense.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.dense.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.embed_q.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.embed_q.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.embed_q.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.kv_a_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.kv_a_proj_with_mqa.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.kv_a_proj_with_mqa.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.kv_a_proj_with_mqa.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_a_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_a_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_a_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_a_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_b_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_b_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.q_b_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.unembed_out.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.unembed_out.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.attention.unembed_out.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.gate.expert_bias": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.gate.gate_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.gate.gate_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.gate.gate_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.dense.biases": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.dense.scales": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.dense.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.g_norm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.g_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.g_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.g_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.key_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.query_key_value.biases": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.query_key_value.scales": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.query_key_value.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.attention.query_layernorm.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.gate.expert_bias": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.gate.gate_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.gate.gate_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.gate.gate_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00004-of-00017.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.dense.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.dense.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.dense.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.g_norm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.g_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.g_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.g_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.key_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.query_key_value.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.query_key_value.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.query_key_value.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.attention.query_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.gate.expert_bias": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.gate.gate_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.gate.gate_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.gate.gate_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00005-of-00017.safetensors", |
| "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00005-of-00017.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00017.safetensors", |
| "model.norm.weight": "model-00017-of-00017.safetensors", |
| "model.word_embeddings.biases": "model-00001-of-00017.safetensors", |
| "model.word_embeddings.scales": "model-00001-of-00017.safetensors", |
| "model.word_embeddings.weight": "model-00001-of-00017.safetensors" |
| } |
| } |
