stablelm-ft / model.safetensors.index.json
TinyPixel's picture
Upload StableLMAlphaForCausalLM
fbf3690
{
"metadata": {
"total_size": 5591869440
},
"weight_map": {
"lm_head.weight": "model-00002-of-00002.safetensors",
"transformer.embed.weight": "model-00001-of-00002.safetensors",
"transformer.final_norm.bias": "model-00002-of-00002.safetensors",
"transformer.final_norm.weight": "model-00002-of-00002.safetensors",
"transformer.layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.0.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.0.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.0.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.0.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.1.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.1.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.1.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.1.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.10.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.10.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.10.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.10.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.11.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.11.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.11.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.11.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.12.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.12.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.12.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.12.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.13.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.13.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.13.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.13.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.14.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.14.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.14.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.14.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.15.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.15.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.15.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.15.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.16.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.16.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.16.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.16.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.17.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.17.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.17.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.17.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.18.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.18.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.18.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.18.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.19.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.19.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.19.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.19.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.2.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.2.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.2.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.2.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.20.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.20.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.20.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.20.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.21.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.21.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.21.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.21.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.22.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.22.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.22.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.22.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.22.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.23.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.23.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.23.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.23.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.23.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.24.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.24.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.24.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.24.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.24.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.25.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.25.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.25.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.25.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.25.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.26.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.26.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.26.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.26.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.26.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.27.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.27.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.27.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.27.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.27.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.28.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.28.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.28.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.28.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.28.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.29.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.29.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.29.mlp.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.29.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.29.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.3.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.3.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.3.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.3.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.30.attention.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.30.attention.qkv_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.30.mlp.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.30.norm.bias": "model-00002-of-00002.safetensors",
"transformer.layers.30.norm.weight": "model-00002-of-00002.safetensors",
"transformer.layers.31.attention.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.31.attention.qkv_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.31.mlp.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.layers.31.norm.bias": "model-00002-of-00002.safetensors",
"transformer.layers.31.norm.weight": "model-00002-of-00002.safetensors",
"transformer.layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.4.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.4.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.4.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.4.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.5.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.5.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.5.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.5.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.6.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.6.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.6.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.6.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.7.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.7.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.7.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.7.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.8.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.8.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.8.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.8.norm.weight": "model-00001-of-00002.safetensors",
"transformer.layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.9.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.9.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.layers.9.norm.bias": "model-00001-of-00002.safetensors",
"transformer.layers.9.norm.weight": "model-00001-of-00002.safetensors"
}
}