I would like to merge the deepseekForCausalLM model. Are there any related examples available?

[xaiocaibi]

I would like to merge the deepseekForCausalLM model. Are there any related examples available?

model.index.json
{
"metadata": {
"total_size": 494385573888
},
"weight_map": {
"lm_head.weight": "pytorch_model-00100-of-00100.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00100.bin",
"model.layers.0.mlp.experts.0.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.0.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.0.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.1.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.1.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.1.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.10.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.10.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.10.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.100.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.100.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.100.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.101.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.101.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.101.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.102.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.102.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.102.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.103.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.103.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.103.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.104.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.104.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.104.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.105.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.105.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.105.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.106.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.106.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.106.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.107.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.107.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.107.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.108.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.108.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.108.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.109.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.109.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.109.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.11.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.11.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.11.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.110.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.110.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.110.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.111.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.111.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.111.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.12.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.12.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.12.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.13.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.13.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.13.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.14.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.14.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.14.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.15.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.15.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.15.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.16.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.16.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.16.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.17.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.17.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.17.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.18.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.18.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.18.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.19.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.19.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.19.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.2.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.2.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.2.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.20.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.20.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.20.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.21.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.21.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.21.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.22.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.22.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.22.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.23.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.23.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.23.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.24.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.24.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.24.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.25.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.25.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.25.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.26.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.26.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.26.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.27.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.27.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.27.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.28.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.28.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.28.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.29.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.29.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.29.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.3.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.3.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.3.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.30.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.30.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.30.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.31.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.31.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.31.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.32.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.32.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.32.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.33.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.33.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.33.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.34.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.34.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.34.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.35.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.35.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.35.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.36.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.36.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.36.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.37.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.37.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.37.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.38.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.38.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.38.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.39.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.39.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.39.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.4.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.4.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.4.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.40.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.40.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.40.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.41.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.41.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.41.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.42.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.42.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.42.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.43.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.43.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.43.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.44.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.44.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.44.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.45.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.45.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.45.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.46.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.46.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.46.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.47.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.47.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.47.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.48.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.48.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.48.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.49.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.49.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.49.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.5.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.5.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.5.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.50.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.50.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.50.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.51.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.51.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.51.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.52.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.52.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.52.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.53.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.53.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.53.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.54.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.54.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.54.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.55.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.55.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.55.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.56.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.56.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.56.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.57.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.57.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.57.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.58.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.58.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.58.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.59.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.59.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.59.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.6.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.6.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.6.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.60.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.60.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.60.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.61.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.61.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.61.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.62.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.62.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.62.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.63.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.63.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.63.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.64.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.64.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.64.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.65.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.65.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.65.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.66.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.66.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.66.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.67.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.67.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.67.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.68.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.68.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.68.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.69.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.69.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.69.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.7.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.7.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.7.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.70.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.70.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.70.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.71.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.71.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.71.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.72.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.72.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.72.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.73.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.73.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.73.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.74.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.74.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.74.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.75.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.75.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.75.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.76.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.76.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.76.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.77.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.77.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.77.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.78.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.78.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.78.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.79.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.79.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.79.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.8.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.8.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.8.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.80.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.80.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.80.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.81.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.81.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.81.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.82.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.82.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.82.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.83.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.83.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.83.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.84.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.84.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.84.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.85.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.85.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.85.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.86.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.86.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.86.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.87.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.87.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.87.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.88.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.88.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.88.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.89.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.89.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.89.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.9.down_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.9.gate_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.9.up_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.mlp.experts.90.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.90.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.90.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.91.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.91.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.91.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.92.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.92.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.92.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.93.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.93.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.93.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.94.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.94.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.94.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.95.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.95.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.95.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.96.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.96.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.96.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.97.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.97.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.97.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.98.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.98.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.98.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.99.down_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.99.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.experts.99.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.gate.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.shared_experts.down_proj.weight": "pytorch_model-00003-of-00100.bin",
"model.layers.0.mlp.shared_experts.gate_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.mlp.shared_experts.up_proj.weight": "pytorch_model-00002-of-00100.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00100.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00100.bin",
"model.norm.weight": "pytorch_model-00099-of-00100.bin"
}
}