model.safetensors.index.json

{
  "metadata": {
    "total_size": 16466072064
  },
  "weight_map": {
    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
    "model.final_layernorm.weight": "model-00004-of-00004.safetensors",
    "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.A_log": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.D": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.b_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.c_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.0.down_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.0.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.0.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.1.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.1.gate_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.1.up_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.2.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.2.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.2.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.3.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.3.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.3.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.4.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.4.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.4.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.5.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.5.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.5.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.6.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.6.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.6.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.7.down_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.7.gate_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.experts.7.up_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.feed_forward.router.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.1.mamba.A_log": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.D": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.b_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.c_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.mamba.x_proj.weight": "model-00001-of-00004.safetensors",
    "model.layers.1.pre_ff_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.feed_forward.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.2.feed_forward.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.2.feed_forward.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.2.mamba.A_log": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.D": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.b_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.c_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.conv1d.bias": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.conv1d.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.dt_layernorm.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.dt_proj.bias": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.dt_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.in_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.out_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.mamba.x_proj.weight": "model-00002-of-00004.safetensors",
    "model.layers.2.pre_ff_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.0.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.0.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.0.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.1.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.1.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.1.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.2.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.2.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.2.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.3.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.3.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.3.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.4.down_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.4.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.4.up_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.5.down_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.5.gate_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.5.up_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.6.down_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.6.gate_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.6.up_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.7.down_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.7.gate_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.experts.7.up_proj.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.feed_forward.router.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
    "model.layers.3.mamba.A_log": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.D": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.b_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.c_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.conv1d.bias": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.conv1d.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.dt_layernorm.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.dt_proj.bias": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.dt_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.in_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.out_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.mamba.x_proj.weight": "model-00003-of-00004.safetensors",
    "model.layers.3.pre_ff_layernorm.weight": "model-00004-of-00004.safetensors"
  }
}