| { |
| "metadata": { |
| "total_size": 1739238144, |
| "total_parameters": 3027074432 |
| }, |
| "weight_map": { |
| "model.embed_tokens.biases": "model.safetensors", |
| "model.embed_tokens.scales": "model.safetensors", |
| "model.embed_tokens.weight": "model.safetensors", |
| "model.final_layernorm.weight": "model.safetensors", |
| "model.layers.0.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.0.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.0.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.0.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.0.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.0.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.0.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.0.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.0.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.0.input_layernorm.weight": "model.safetensors", |
| "model.layers.0.mamba.A_log": "model.safetensors", |
| "model.layers.0.mamba.D": "model.safetensors", |
| "model.layers.0.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.0.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.0.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.0.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.0.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.0.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.0.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.0.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.0.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.0.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.0.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.0.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.0.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.0.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.0.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.0.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.0.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.1.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.1.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.1.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.1.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.1.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.1.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.1.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.1.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.1.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.1.input_layernorm.weight": "model.safetensors", |
| "model.layers.1.mamba.A_log": "model.safetensors", |
| "model.layers.1.mamba.D": "model.safetensors", |
| "model.layers.1.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.1.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.1.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.1.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.1.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.1.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.1.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.1.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.1.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.1.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.1.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.1.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.1.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.1.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.1.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.1.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.1.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.10.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.10.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.10.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.10.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.10.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.10.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.10.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.10.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.10.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.10.input_layernorm.weight": "model.safetensors", |
| "model.layers.10.mamba.A_log": "model.safetensors", |
| "model.layers.10.mamba.D": "model.safetensors", |
| "model.layers.10.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.10.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.10.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.10.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.10.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.10.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.10.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.10.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.10.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.10.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.10.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.10.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.10.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.10.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.10.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.10.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.10.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.11.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.11.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.11.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.11.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.11.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.11.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.11.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.11.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.11.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.11.input_layernorm.weight": "model.safetensors", |
| "model.layers.11.mamba.A_log": "model.safetensors", |
| "model.layers.11.mamba.D": "model.safetensors", |
| "model.layers.11.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.11.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.11.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.11.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.11.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.11.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.11.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.11.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.11.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.11.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.11.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.11.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.11.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.11.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.11.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.11.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.11.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.12.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.12.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.12.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.12.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.12.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.12.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.12.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.12.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.12.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.12.input_layernorm.weight": "model.safetensors", |
| "model.layers.12.mamba.A_log": "model.safetensors", |
| "model.layers.12.mamba.D": "model.safetensors", |
| "model.layers.12.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.12.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.12.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.12.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.12.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.12.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.12.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.12.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.12.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.12.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.12.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.12.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.12.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.12.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.12.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.12.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.12.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.13.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.13.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.13.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.13.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.13.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.13.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.13.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.13.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.13.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.13.input_layernorm.weight": "model.safetensors", |
| "model.layers.13.mamba.A_log": "model.safetensors", |
| "model.layers.13.mamba.D": "model.safetensors", |
| "model.layers.13.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.13.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.13.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.13.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.13.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.13.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.13.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.13.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.13.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.13.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.13.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.13.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.13.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.13.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.13.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.13.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.13.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.14.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.14.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.14.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.14.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.14.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.14.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.14.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.14.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.14.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.14.input_layernorm.weight": "model.safetensors", |
| "model.layers.14.mamba.A_log": "model.safetensors", |
| "model.layers.14.mamba.D": "model.safetensors", |
| "model.layers.14.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.14.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.14.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.14.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.14.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.14.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.14.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.14.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.14.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.14.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.14.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.14.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.14.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.14.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.14.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.14.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.14.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.15.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.15.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.15.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.15.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.15.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.15.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.15.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.15.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.15.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.15.input_layernorm.weight": "model.safetensors", |
| "model.layers.15.mamba.A_log": "model.safetensors", |
| "model.layers.15.mamba.D": "model.safetensors", |
| "model.layers.15.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.15.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.15.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.15.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.15.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.15.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.15.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.15.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.15.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.15.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.15.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.15.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.15.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.15.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.15.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.15.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.15.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.16.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.16.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.16.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.16.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.16.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.16.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.16.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.16.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.16.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.16.input_layernorm.weight": "model.safetensors", |
| "model.layers.16.mamba.A_log": "model.safetensors", |
| "model.layers.16.mamba.D": "model.safetensors", |
| "model.layers.16.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.16.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.16.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.16.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.16.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.16.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.16.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.16.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.16.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.16.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.16.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.16.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.16.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.16.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.16.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.16.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.16.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.17.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.17.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.17.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.17.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.17.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.17.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.17.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.17.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.17.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.17.input_layernorm.weight": "model.safetensors", |
| "model.layers.17.mamba.A_log": "model.safetensors", |
| "model.layers.17.mamba.D": "model.safetensors", |
| "model.layers.17.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.17.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.17.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.17.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.17.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.17.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.17.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.17.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.17.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.17.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.17.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.17.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.17.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.17.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.17.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.17.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.17.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.18.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.18.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.18.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.18.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.18.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.18.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.18.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.18.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.18.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.18.input_layernorm.weight": "model.safetensors", |
| "model.layers.18.mamba.A_log": "model.safetensors", |
| "model.layers.18.mamba.D": "model.safetensors", |
| "model.layers.18.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.18.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.18.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.18.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.18.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.18.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.18.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.18.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.18.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.18.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.18.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.18.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.18.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.18.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.18.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.18.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.18.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.19.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.19.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.19.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.19.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.19.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.19.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.19.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.19.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.19.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.19.input_layernorm.weight": "model.safetensors", |
| "model.layers.19.mamba.A_log": "model.safetensors", |
| "model.layers.19.mamba.D": "model.safetensors", |
| "model.layers.19.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.19.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.19.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.19.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.19.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.19.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.19.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.19.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.19.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.19.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.19.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.19.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.19.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.19.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.19.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.19.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.19.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.2.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.2.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.2.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.2.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.2.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.2.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.2.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.2.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.2.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.2.input_layernorm.weight": "model.safetensors", |
| "model.layers.2.mamba.A_log": "model.safetensors", |
| "model.layers.2.mamba.D": "model.safetensors", |
| "model.layers.2.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.2.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.2.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.2.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.2.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.2.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.2.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.2.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.2.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.2.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.2.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.2.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.2.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.2.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.2.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.2.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.2.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.20.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.20.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.20.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.20.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.20.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.20.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.20.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.20.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.20.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.20.input_layernorm.weight": "model.safetensors", |
| "model.layers.20.mamba.A_log": "model.safetensors", |
| "model.layers.20.mamba.D": "model.safetensors", |
| "model.layers.20.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.20.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.20.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.20.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.20.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.20.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.20.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.20.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.20.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.20.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.20.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.20.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.20.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.20.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.20.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.20.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.20.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.21.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.21.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.21.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.21.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.21.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.21.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.21.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.21.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.21.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.21.input_layernorm.weight": "model.safetensors", |
| "model.layers.21.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.21.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.21.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.21.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.21.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.21.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.21.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.21.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.21.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.22.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.22.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.22.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.22.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.22.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.22.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.22.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.22.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.22.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.22.input_layernorm.weight": "model.safetensors", |
| "model.layers.22.mamba.A_log": "model.safetensors", |
| "model.layers.22.mamba.D": "model.safetensors", |
| "model.layers.22.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.22.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.22.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.22.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.22.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.22.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.22.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.22.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.22.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.22.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.22.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.22.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.22.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.22.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.22.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.22.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.22.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.23.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.23.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.23.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.23.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.23.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.23.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.23.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.23.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.23.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.23.input_layernorm.weight": "model.safetensors", |
| "model.layers.23.mamba.A_log": "model.safetensors", |
| "model.layers.23.mamba.D": "model.safetensors", |
| "model.layers.23.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.23.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.23.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.23.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.23.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.23.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.23.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.23.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.23.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.23.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.23.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.23.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.23.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.23.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.23.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.23.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.23.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.24.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.24.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.24.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.24.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.24.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.24.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.24.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.24.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.24.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.24.input_layernorm.weight": "model.safetensors", |
| "model.layers.24.mamba.A_log": "model.safetensors", |
| "model.layers.24.mamba.D": "model.safetensors", |
| "model.layers.24.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.24.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.24.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.24.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.24.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.24.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.24.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.24.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.24.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.24.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.24.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.24.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.24.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.24.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.24.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.24.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.24.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.25.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.25.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.25.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.25.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.25.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.25.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.25.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.25.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.25.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.25.input_layernorm.weight": "model.safetensors", |
| "model.layers.25.mamba.A_log": "model.safetensors", |
| "model.layers.25.mamba.D": "model.safetensors", |
| "model.layers.25.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.25.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.25.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.25.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.25.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.25.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.25.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.25.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.25.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.25.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.25.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.25.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.25.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.25.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.25.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.25.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.25.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.26.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.26.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.26.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.26.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.26.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.26.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.26.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.26.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.26.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.26.input_layernorm.weight": "model.safetensors", |
| "model.layers.26.mamba.A_log": "model.safetensors", |
| "model.layers.26.mamba.D": "model.safetensors", |
| "model.layers.26.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.26.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.26.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.26.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.26.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.26.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.26.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.26.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.26.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.26.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.26.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.26.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.26.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.26.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.26.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.26.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.26.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.27.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.27.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.27.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.27.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.27.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.27.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.27.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.27.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.27.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.27.input_layernorm.weight": "model.safetensors", |
| "model.layers.27.mamba.A_log": "model.safetensors", |
| "model.layers.27.mamba.D": "model.safetensors", |
| "model.layers.27.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.27.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.27.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.27.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.27.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.27.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.27.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.27.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.27.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.27.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.27.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.27.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.27.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.27.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.27.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.27.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.27.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.3.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.3.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.3.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.3.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.3.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.3.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.3.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.3.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.3.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.3.input_layernorm.weight": "model.safetensors", |
| "model.layers.3.mamba.A_log": "model.safetensors", |
| "model.layers.3.mamba.D": "model.safetensors", |
| "model.layers.3.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.3.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.3.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.3.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.3.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.3.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.3.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.3.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.3.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.3.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.3.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.3.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.3.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.3.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.3.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.3.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.3.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.4.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.4.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.4.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.4.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.4.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.4.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.4.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.4.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.4.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.4.input_layernorm.weight": "model.safetensors", |
| "model.layers.4.mamba.A_log": "model.safetensors", |
| "model.layers.4.mamba.D": "model.safetensors", |
| "model.layers.4.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.4.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.4.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.4.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.4.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.4.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.4.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.4.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.4.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.4.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.4.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.4.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.4.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.4.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.4.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.4.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.4.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.5.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.5.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.5.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.5.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.5.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.5.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.5.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.5.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.5.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.5.input_layernorm.weight": "model.safetensors", |
| "model.layers.5.mamba.A_log": "model.safetensors", |
| "model.layers.5.mamba.D": "model.safetensors", |
| "model.layers.5.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.5.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.5.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.5.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.5.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.5.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.5.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.5.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.5.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.5.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.5.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.5.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.5.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.5.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.5.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.5.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.5.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.6.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.6.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.6.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.6.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.6.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.6.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.6.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.6.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.6.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.6.input_layernorm.weight": "model.safetensors", |
| "model.layers.6.mamba.A_log": "model.safetensors", |
| "model.layers.6.mamba.D": "model.safetensors", |
| "model.layers.6.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.6.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.6.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.6.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.6.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.6.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.6.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.6.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.6.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.6.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.6.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.6.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.6.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.6.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.6.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.6.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.6.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.7.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.7.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.7.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.7.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.7.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.7.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.7.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.7.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.7.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.7.input_layernorm.weight": "model.safetensors", |
| "model.layers.7.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.o_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.o_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.q_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.q_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.biases": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.scales": "model.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model.safetensors", |
| "model.layers.8.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.8.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.8.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.8.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.8.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.8.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.8.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.8.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.8.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.8.input_layernorm.weight": "model.safetensors", |
| "model.layers.8.mamba.A_log": "model.safetensors", |
| "model.layers.8.mamba.D": "model.safetensors", |
| "model.layers.8.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.8.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.8.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.8.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.8.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.8.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.8.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.8.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.8.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.8.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.8.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.8.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.8.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.8.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.8.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.8.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.8.pre_ff_layernorm.weight": "model.safetensors", |
| "model.layers.9.feed_forward.down_proj.biases": "model.safetensors", |
| "model.layers.9.feed_forward.down_proj.scales": "model.safetensors", |
| "model.layers.9.feed_forward.down_proj.weight": "model.safetensors", |
| "model.layers.9.feed_forward.gate_proj.biases": "model.safetensors", |
| "model.layers.9.feed_forward.gate_proj.scales": "model.safetensors", |
| "model.layers.9.feed_forward.gate_proj.weight": "model.safetensors", |
| "model.layers.9.feed_forward.up_proj.biases": "model.safetensors", |
| "model.layers.9.feed_forward.up_proj.scales": "model.safetensors", |
| "model.layers.9.feed_forward.up_proj.weight": "model.safetensors", |
| "model.layers.9.input_layernorm.weight": "model.safetensors", |
| "model.layers.9.mamba.A_log": "model.safetensors", |
| "model.layers.9.mamba.D": "model.safetensors", |
| "model.layers.9.mamba.b_layernorm.weight": "model.safetensors", |
| "model.layers.9.mamba.c_layernorm.weight": "model.safetensors", |
| "model.layers.9.mamba.conv1d.bias": "model.safetensors", |
| "model.layers.9.mamba.conv1d.weight": "model.safetensors", |
| "model.layers.9.mamba.dt_layernorm.weight": "model.safetensors", |
| "model.layers.9.mamba.dt_proj.bias": "model.safetensors", |
| "model.layers.9.mamba.dt_proj.weight": "model.safetensors", |
| "model.layers.9.mamba.in_proj.biases": "model.safetensors", |
| "model.layers.9.mamba.in_proj.scales": "model.safetensors", |
| "model.layers.9.mamba.in_proj.weight": "model.safetensors", |
| "model.layers.9.mamba.out_proj.biases": "model.safetensors", |
| "model.layers.9.mamba.out_proj.scales": "model.safetensors", |
| "model.layers.9.mamba.out_proj.weight": "model.safetensors", |
| "model.layers.9.mamba.x_proj.biases": "model.safetensors", |
| "model.layers.9.mamba.x_proj.scales": "model.safetensors", |
| "model.layers.9.mamba.x_proj.weight": "model.safetensors", |
| "model.layers.9.pre_ff_layernorm.weight": "model.safetensors" |
| } |
| } |
