jetmoe-8b / model.safetensors.index.json
YikangS's picture
change weight format
e289db5
{
"metadata": {
"total_size": 17044475904
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.13.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.14.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.15.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.bias": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.20.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.input_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.output_linear.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.experts.router.layer.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attention.kv_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.bias": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.bias": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.21.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.bias": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.bias": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.22.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.bias": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.mlp.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.bias": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.input_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.output_linear.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.experts.router.layer.weight": "model-00004-of-00004.safetensors",
"model.layers.23.self_attention.kv_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.bias": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.bias": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.input_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.output_linear.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.experts.router.layer.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attention.kv_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.bias": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.input_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.output_linear.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.experts.router.layer.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attention.kv_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}