Files
DS4Server/tests/fixtures/mtplx-binding.jsonl
T

5 lines
149 KiB
JSON

{"mask":0,"mtp":false,"parameter_count":2466,"metadata_sha256":"b33146c5e762ebff20827a3c1e3d000a13fe09056ac89dc4e32da939e4d96abe","quantized":{"language_model.lm_head":[4,64,[248320,320]],"language_model.model.layers.47.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.47.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.47.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.47.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.47.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.47.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.47.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.47.mlp.gate":[8,64,[512,640]],"language_model.model.layers.47.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.47.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.47.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.47.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.47.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.46.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.46.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.46.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.46.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.46.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.46.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.46.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.46.mlp.gate":[8,64,[512,640]],"language_model.model.layers.46.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.46.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.46.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.46.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.46.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.45.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.45.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.45.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.45.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.45.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.45.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.45.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.45.mlp.gate":[8,64,[512,640]],"language_model.model.layers.45.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.45.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.45.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.45.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.45.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.44.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.44.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.44.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.44.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.44.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.44.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.44.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.44.mlp.gate":[8,64,[512,640]],"language_model.model.layers.44.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.44.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.44.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.44.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.44.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.43.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.43.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.43.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.43.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.43.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.43.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.43.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.43.mlp.gate":[8,64,[512,640]],"language_model.model.layers.43.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.43.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.43.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.43.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.43.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.42.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.42.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.42.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.42.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.42.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.42.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.42.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.42.mlp.gate":[8,64,[512,640]],"language_model.model.layers.42.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.42.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.42.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.42.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.42.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.41.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.41.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.41.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.41.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.41.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.41.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.41.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.41.mlp.gate":[8,64,[512,640]],"language_model.model.layers.41.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.41.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.41.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.41.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.41.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.40.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.40.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.40.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.40.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.40.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.40.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.40.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.40.mlp.gate":[8,64,[512,640]],"language_model.model.layers.40.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.40.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.40.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.40.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.40.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.39.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.39.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.39.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.39.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.39.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.39.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.39.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.39.mlp.gate":[8,64,[512,640]],"language_model.model.layers.39.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.39.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.39.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.39.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.39.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.38.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.38.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.38.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.38.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.38.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.38.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.38.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.38.mlp.gate":[8,64,[512,640]],"language_model.model.layers.38.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.38.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.38.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.38.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.38.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.37.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.37.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.37.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.37.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.37.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.37.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.37.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.37.mlp.gate":[8,64,[512,640]],"language_model.model.layers.37.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.37.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.37.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.37.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.37.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.36.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.36.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.36.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.36.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.36.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.36.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.36.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.36.mlp.gate":[8,64,[512,640]],"language_model.model.layers.36.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.36.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.36.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.36.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.36.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.35.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.35.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.35.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.35.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.35.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.35.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.35.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.35.mlp.gate":[8,64,[512,640]],"language_model.model.layers.35.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.35.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.35.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.35.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.35.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.34.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.34.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.34.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.34.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.34.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.34.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.34.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.34.mlp.gate":[8,64,[512,640]],"language_model.model.layers.34.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.34.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.34.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.34.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.34.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.33.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.33.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.33.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.33.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.33.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.33.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.33.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.33.mlp.gate":[8,64,[512,640]],"language_model.model.layers.33.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.33.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.33.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.33.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.33.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.32.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.32.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.32.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.32.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.32.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.32.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.32.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.32.mlp.gate":[8,64,[512,640]],"language_model.model.layers.32.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.32.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.32.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.32.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.32.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.31.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.31.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.31.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.31.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.31.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.31.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.31.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.31.mlp.gate":[8,64,[512,640]],"language_model.model.layers.31.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.31.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.31.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.31.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.31.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.30.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.30.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.30.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.30.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.30.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.30.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.30.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.30.mlp.gate":[8,64,[512,640]],"language_model.model.layers.30.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.30.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.30.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.30.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.30.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.29.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.29.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.29.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.29.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.29.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.29.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.29.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.29.mlp.gate":[8,64,[512,640]],"language_model.model.layers.29.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.29.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.29.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.29.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.29.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.28.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.28.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.28.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.28.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.28.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.28.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.28.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.28.mlp.gate":[8,64,[512,640]],"language_model.model.layers.28.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.28.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.28.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.28.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.28.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.27.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.27.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.27.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.27.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.27.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.27.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.27.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.27.mlp.gate":[8,64,[512,640]],"language_model.model.layers.27.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.27.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.27.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.27.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.27.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.26.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.26.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.26.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.26.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.26.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.26.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.26.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.26.mlp.gate":[8,64,[512,640]],"language_model.model.layers.26.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.26.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.26.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.26.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.26.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.25.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.25.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.25.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.25.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.25.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.25.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.25.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.25.mlp.gate":[8,64,[512,640]],"language_model.model.layers.25.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.25.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.25.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.25.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.25.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.24.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.24.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.24.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.24.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.24.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.24.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.24.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.24.mlp.gate":[8,64,[512,640]],"language_model.model.layers.24.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.24.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.24.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.24.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.24.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.23.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.23.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.23.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.23.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.23.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.23.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.23.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.23.mlp.gate":[8,64,[512,640]],"language_model.model.layers.23.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.23.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.23.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.23.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.23.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.22.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.22.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.22.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.22.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.22.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.22.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.22.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.22.mlp.gate":[8,64,[512,640]],"language_model.model.layers.22.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.22.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.22.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.22.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.22.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.21.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.21.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.21.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.21.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.21.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.21.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.21.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.21.mlp.gate":[8,64,[512,640]],"language_model.model.layers.21.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.21.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.21.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.21.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.21.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.20.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.20.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.20.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.20.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.20.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.20.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.20.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.20.mlp.gate":[8,64,[512,640]],"language_model.model.layers.20.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.20.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.20.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.20.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.20.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.19.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.19.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.19.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.19.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.19.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.19.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.19.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.19.mlp.gate":[8,64,[512,640]],"language_model.model.layers.19.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.19.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.19.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.19.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.19.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.18.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.18.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.18.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.18.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.18.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.18.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.18.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.18.mlp.gate":[8,64,[512,640]],"language_model.model.layers.18.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.18.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.18.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.18.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.18.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.17.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.17.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.17.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.17.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.17.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.17.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.17.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.17.mlp.gate":[8,64,[512,640]],"language_model.model.layers.17.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.17.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.17.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.17.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.17.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.16.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.16.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.16.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.16.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.16.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.16.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.16.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.16.mlp.gate":[8,64,[512,640]],"language_model.model.layers.16.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.16.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.16.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.16.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.16.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.15.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.15.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.15.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.15.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.15.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.15.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.15.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.15.mlp.gate":[8,64,[512,640]],"language_model.model.layers.15.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.15.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.15.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.15.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.15.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.14.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.14.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.14.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.14.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.14.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.14.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.14.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.14.mlp.gate":[8,64,[512,640]],"language_model.model.layers.14.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.14.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.14.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.14.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.14.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.13.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.13.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.13.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.13.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.13.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.13.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.13.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.13.mlp.gate":[8,64,[512,640]],"language_model.model.layers.13.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.13.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.13.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.13.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.13.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.12.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.12.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.12.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.12.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.12.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.12.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.12.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.12.mlp.gate":[8,64,[512,640]],"language_model.model.layers.12.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.12.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.12.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.12.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.12.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.11.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.11.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.11.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.11.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.11.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.11.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.11.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.11.mlp.gate":[8,64,[512,640]],"language_model.model.layers.11.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.11.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.11.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.11.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.11.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.10.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.10.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.10.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.10.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.10.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.10.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.10.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.10.mlp.gate":[8,64,[512,640]],"language_model.model.layers.10.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.10.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.10.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.10.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.10.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.9.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.9.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.9.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.9.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.9.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.9.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.9.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.9.mlp.gate":[8,64,[512,640]],"language_model.model.layers.9.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.9.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.9.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.9.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.9.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.8.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.8.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.8.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.8.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.8.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.8.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.8.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.8.mlp.gate":[8,64,[512,640]],"language_model.model.layers.8.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.8.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.8.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.8.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.8.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.7.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.7.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.7.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.7.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.7.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.7.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.7.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.7.mlp.gate":[8,64,[512,640]],"language_model.model.layers.7.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.7.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.7.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.7.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.7.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.6.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.6.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.6.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.6.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.6.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.6.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.6.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.6.mlp.gate":[8,64,[512,640]],"language_model.model.layers.6.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.6.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.6.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.6.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.6.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.5.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.5.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.5.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.5.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.5.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.5.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.5.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.5.mlp.gate":[8,64,[512,640]],"language_model.model.layers.5.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.5.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.5.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.5.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.5.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.4.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.4.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.4.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.4.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.4.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.4.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.4.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.4.mlp.gate":[8,64,[512,640]],"language_model.model.layers.4.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.4.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.4.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.4.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.4.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.3.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.3.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.3.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.3.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.3.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.3.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.3.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.3.mlp.gate":[8,64,[512,640]],"language_model.model.layers.3.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.3.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.3.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.3.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.3.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.2.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.2.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.2.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.2.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.2.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.2.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.2.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.2.mlp.gate":[8,64,[512,640]],"language_model.model.layers.2.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.2.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.2.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.2.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.2.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.1.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.1.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.1.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.1.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.1.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.1.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.1.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.1.mlp.gate":[8,64,[512,640]],"language_model.model.layers.1.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.1.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.1.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.1.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.1.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.0.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.0.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.0.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.0.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.0.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.0.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.0.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.0.mlp.gate":[8,64,[512,640]],"language_model.model.layers.0.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.0.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.0.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.0.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.0.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.embed_tokens":[4,64,[248320,320]]},"norms":{},"ple":[1],"linear":[0,1,2,4,5,6,8,9,10,12,13,14,16,17,18,20,21,22,24,25,26,28,29,30,32,33,34,36,37,38,40,41,42,44,45,46]}
{"mask":7,"mtp":false,"parameter_count":1782,"metadata_sha256":"fb7106c8a24a6dc1073cbc386d57c9e60a9f30858ecf294bd9bba215b1bfa8b8","quantized":{"language_model.lm_head":[4,64,[248320,320]],"language_model.model.layers.47.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.47.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.47.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.47.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.47.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.47.mlp.gate":[8,64,[512,640]],"language_model.model.layers.47.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.47.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.47.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.46.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.46.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.46.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.46.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.46.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.46.mlp.gate":[8,64,[512,640]],"language_model.model.layers.46.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.46.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.45.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.45.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.45.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.45.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.45.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.45.mlp.gate":[8,64,[512,640]],"language_model.model.layers.45.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.45.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.44.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.44.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.44.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.44.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.44.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.44.mlp.gate":[8,64,[512,640]],"language_model.model.layers.44.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.44.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.43.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.43.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.43.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.43.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.43.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.43.mlp.gate":[8,64,[512,640]],"language_model.model.layers.43.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.43.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.43.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.42.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.42.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.42.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.42.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.42.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.42.mlp.gate":[8,64,[512,640]],"language_model.model.layers.42.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.42.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.41.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.41.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.41.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.41.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.41.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.41.mlp.gate":[8,64,[512,640]],"language_model.model.layers.41.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.41.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.40.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.40.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.40.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.40.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.40.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.40.mlp.gate":[8,64,[512,640]],"language_model.model.layers.40.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.40.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.39.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.39.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.39.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.39.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.39.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.39.mlp.gate":[8,64,[512,640]],"language_model.model.layers.39.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.39.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.39.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.38.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.38.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.38.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.38.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.38.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.38.mlp.gate":[8,64,[512,640]],"language_model.model.layers.38.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.38.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.37.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.37.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.37.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.37.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.37.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.37.mlp.gate":[8,64,[512,640]],"language_model.model.layers.37.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.37.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.36.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.36.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.36.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.36.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.36.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.36.mlp.gate":[8,64,[512,640]],"language_model.model.layers.36.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.36.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.35.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.35.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.35.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.35.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.35.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.35.mlp.gate":[8,64,[512,640]],"language_model.model.layers.35.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.35.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.35.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.34.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.34.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.34.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.34.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.34.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.34.mlp.gate":[8,64,[512,640]],"language_model.model.layers.34.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.34.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.33.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.33.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.33.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.33.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.33.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.33.mlp.gate":[8,64,[512,640]],"language_model.model.layers.33.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.33.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.32.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.32.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.32.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.32.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.32.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.32.mlp.gate":[8,64,[512,640]],"language_model.model.layers.32.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.32.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.31.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.31.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.31.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.31.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.31.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.31.mlp.gate":[8,64,[512,640]],"language_model.model.layers.31.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.31.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.31.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.30.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.30.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.30.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.30.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.30.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.30.mlp.gate":[8,64,[512,640]],"language_model.model.layers.30.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.30.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.29.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.29.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.29.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.29.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.29.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.29.mlp.gate":[8,64,[512,640]],"language_model.model.layers.29.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.29.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.28.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.28.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.28.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.28.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.28.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.28.mlp.gate":[8,64,[512,640]],"language_model.model.layers.28.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.28.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.27.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.27.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.27.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.27.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.27.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.27.mlp.gate":[8,64,[512,640]],"language_model.model.layers.27.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.27.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.27.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.26.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.26.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.26.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.26.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.26.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.26.mlp.gate":[8,64,[512,640]],"language_model.model.layers.26.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.26.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.25.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.25.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.25.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.25.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.25.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.25.mlp.gate":[8,64,[512,640]],"language_model.model.layers.25.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.25.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.24.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.24.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.24.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.24.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.24.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.24.mlp.gate":[8,64,[512,640]],"language_model.model.layers.24.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.24.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.23.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.23.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.23.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.23.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.23.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.23.mlp.gate":[8,64,[512,640]],"language_model.model.layers.23.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.23.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.23.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.22.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.22.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.22.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.22.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.22.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.22.mlp.gate":[8,64,[512,640]],"language_model.model.layers.22.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.22.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.21.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.21.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.21.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.21.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.21.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.21.mlp.gate":[8,64,[512,640]],"language_model.model.layers.21.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.21.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.20.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.20.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.20.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.20.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.20.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.20.mlp.gate":[8,64,[512,640]],"language_model.model.layers.20.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.20.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.19.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.19.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.19.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.19.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.19.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.19.mlp.gate":[8,64,[512,640]],"language_model.model.layers.19.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.19.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.19.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.18.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.18.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.18.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.18.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.18.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.18.mlp.gate":[8,64,[512,640]],"language_model.model.layers.18.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.18.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.17.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.17.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.17.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.17.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.17.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.17.mlp.gate":[8,64,[512,640]],"language_model.model.layers.17.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.17.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.16.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.16.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.16.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.16.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.16.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.16.mlp.gate":[8,64,[512,640]],"language_model.model.layers.16.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.16.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.15.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.15.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.15.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.15.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.15.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.15.mlp.gate":[8,64,[512,640]],"language_model.model.layers.15.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.15.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.15.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.14.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.14.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.14.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.14.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.14.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.14.mlp.gate":[8,64,[512,640]],"language_model.model.layers.14.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.14.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.13.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.13.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.13.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.13.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.13.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.13.mlp.gate":[8,64,[512,640]],"language_model.model.layers.13.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.13.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.12.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.12.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.12.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.12.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.12.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.12.mlp.gate":[8,64,[512,640]],"language_model.model.layers.12.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.12.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.11.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.11.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.11.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.11.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.11.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.11.mlp.gate":[8,64,[512,640]],"language_model.model.layers.11.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.11.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.11.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.10.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.10.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.10.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.10.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.10.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.10.mlp.gate":[8,64,[512,640]],"language_model.model.layers.10.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.10.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.9.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.9.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.9.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.9.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.9.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.9.mlp.gate":[8,64,[512,640]],"language_model.model.layers.9.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.9.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.8.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.8.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.8.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.8.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.8.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.8.mlp.gate":[8,64,[512,640]],"language_model.model.layers.8.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.8.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.7.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.7.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.7.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.7.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.7.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.7.mlp.gate":[8,64,[512,640]],"language_model.model.layers.7.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.7.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.7.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.6.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.6.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.6.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.6.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.6.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.6.mlp.gate":[8,64,[512,640]],"language_model.model.layers.6.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.6.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.5.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.5.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.5.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.5.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.5.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.5.mlp.gate":[8,64,[512,640]],"language_model.model.layers.5.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.5.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.4.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.4.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.4.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.4.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.4.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.4.mlp.gate":[8,64,[512,640]],"language_model.model.layers.4.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.4.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.3.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.3.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.3.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.3.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.3.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.3.mlp.gate":[8,64,[512,640]],"language_model.model.layers.3.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.3.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.3.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.2.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.2.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.2.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.2.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.2.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.2.mlp.gate":[8,64,[512,640]],"language_model.model.layers.2.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.2.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.1.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.1.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.1.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.1.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.1.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.1.mlp.gate":[8,64,[512,640]],"language_model.model.layers.1.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.1.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.0.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.0.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.0.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.0.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.0.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.0.mlp.gate":[8,64,[512,640]],"language_model.model.layers.0.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.0.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.embed_tokens":[4,64,[248320,320]]},"norms":{},"ple":[1],"linear":[0,1,2,4,5,6,8,9,10,12,13,14,16,17,18,20,21,22,24,25,26,28,29,30,32,33,34,36,37,38,40,41,42,44,45,46]}
{"mask":0,"mtp":true,"parameter_count":2524,"metadata_sha256":"506883ab5e2ae423e674c97fdcf437cdcc78da6a4289345eb1a9e75f7cdc1dd1","quantized":{"mtp.layers.0.mlp.shared_expert_gate":[4,64,[1,320]],"mtp.layers.0.mlp.shared_expert.up_proj":[4,64,[640,320]],"mtp.layers.0.mlp.shared_expert.down_proj":[4,64,[2560,80]],"mtp.layers.0.mlp.shared_expert.gate_proj":[4,64,[640,320]],"mtp.layers.0.mlp.switch_mlp.down_proj":[4,32,[512,2560,80]],"mtp.layers.0.mlp.switch_mlp.up_proj":[4,32,[512,640,320]],"mtp.layers.0.mlp.switch_mlp.gate_proj":[4,32,[512,640,320]],"mtp.layers.0.mlp.gate":[8,64,[512,640]],"mtp.layers.0.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"mtp.layers.0.self_attn.o_proj":[4,64,[2560,768]],"mtp.layers.0.self_attn.v_proj":[4,64,[512,320]],"mtp.layers.0.self_attn.k_proj":[4,64,[512,320]],"mtp.layers.0.self_attn.q_proj":[4,64,[12288,320]],"language_model.lm_head":[4,64,[248320,320]],"language_model.model.layers.47.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.47.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.47.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.47.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.47.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.47.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.47.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.47.mlp.gate":[8,64,[512,640]],"language_model.model.layers.47.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.47.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.47.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.47.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.47.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.46.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.46.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.46.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.46.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.46.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.46.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.46.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.46.mlp.gate":[8,64,[512,640]],"language_model.model.layers.46.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.46.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.46.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.46.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.46.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.45.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.45.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.45.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.45.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.45.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.45.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.45.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.45.mlp.gate":[8,64,[512,640]],"language_model.model.layers.45.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.45.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.45.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.45.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.45.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.44.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.44.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.44.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.44.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.44.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.44.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.44.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.44.mlp.gate":[8,64,[512,640]],"language_model.model.layers.44.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.44.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.44.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.44.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.44.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.43.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.43.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.43.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.43.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.43.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.43.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.43.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.43.mlp.gate":[8,64,[512,640]],"language_model.model.layers.43.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.43.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.43.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.43.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.43.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.42.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.42.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.42.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.42.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.42.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.42.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.42.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.42.mlp.gate":[8,64,[512,640]],"language_model.model.layers.42.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.42.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.42.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.42.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.42.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.41.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.41.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.41.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.41.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.41.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.41.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.41.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.41.mlp.gate":[8,64,[512,640]],"language_model.model.layers.41.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.41.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.41.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.41.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.41.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.40.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.40.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.40.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.40.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.40.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.40.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.40.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.40.mlp.gate":[8,64,[512,640]],"language_model.model.layers.40.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.40.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.40.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.40.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.40.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.39.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.39.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.39.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.39.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.39.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.39.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.39.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.39.mlp.gate":[8,64,[512,640]],"language_model.model.layers.39.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.39.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.39.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.39.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.39.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.38.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.38.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.38.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.38.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.38.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.38.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.38.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.38.mlp.gate":[8,64,[512,640]],"language_model.model.layers.38.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.38.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.38.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.38.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.38.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.37.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.37.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.37.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.37.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.37.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.37.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.37.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.37.mlp.gate":[8,64,[512,640]],"language_model.model.layers.37.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.37.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.37.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.37.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.37.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.36.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.36.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.36.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.36.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.36.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.36.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.36.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.36.mlp.gate":[8,64,[512,640]],"language_model.model.layers.36.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.36.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.36.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.36.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.36.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.35.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.35.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.35.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.35.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.35.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.35.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.35.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.35.mlp.gate":[8,64,[512,640]],"language_model.model.layers.35.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.35.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.35.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.35.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.35.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.34.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.34.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.34.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.34.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.34.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.34.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.34.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.34.mlp.gate":[8,64,[512,640]],"language_model.model.layers.34.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.34.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.34.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.34.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.34.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.33.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.33.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.33.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.33.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.33.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.33.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.33.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.33.mlp.gate":[8,64,[512,640]],"language_model.model.layers.33.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.33.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.33.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.33.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.33.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.32.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.32.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.32.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.32.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.32.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.32.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.32.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.32.mlp.gate":[8,64,[512,640]],"language_model.model.layers.32.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.32.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.32.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.32.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.32.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.31.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.31.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.31.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.31.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.31.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.31.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.31.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.31.mlp.gate":[8,64,[512,640]],"language_model.model.layers.31.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.31.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.31.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.31.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.31.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.30.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.30.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.30.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.30.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.30.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.30.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.30.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.30.mlp.gate":[8,64,[512,640]],"language_model.model.layers.30.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.30.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.30.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.30.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.30.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.29.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.29.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.29.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.29.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.29.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.29.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.29.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.29.mlp.gate":[8,64,[512,640]],"language_model.model.layers.29.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.29.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.29.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.29.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.29.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.28.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.28.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.28.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.28.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.28.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.28.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.28.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.28.mlp.gate":[8,64,[512,640]],"language_model.model.layers.28.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.28.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.28.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.28.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.28.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.27.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.27.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.27.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.27.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.27.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.27.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.27.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.27.mlp.gate":[8,64,[512,640]],"language_model.model.layers.27.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.27.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.27.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.27.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.27.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.26.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.26.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.26.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.26.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.26.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.26.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.26.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.26.mlp.gate":[8,64,[512,640]],"language_model.model.layers.26.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.26.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.26.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.26.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.26.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.25.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.25.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.25.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.25.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.25.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.25.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.25.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.25.mlp.gate":[8,64,[512,640]],"language_model.model.layers.25.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.25.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.25.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.25.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.25.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.24.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.24.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.24.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.24.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.24.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.24.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.24.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.24.mlp.gate":[8,64,[512,640]],"language_model.model.layers.24.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.24.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.24.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.24.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.24.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.23.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.23.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.23.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.23.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.23.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.23.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.23.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.23.mlp.gate":[8,64,[512,640]],"language_model.model.layers.23.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.23.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.23.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.23.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.23.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.22.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.22.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.22.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.22.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.22.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.22.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.22.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.22.mlp.gate":[8,64,[512,640]],"language_model.model.layers.22.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.22.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.22.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.22.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.22.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.21.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.21.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.21.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.21.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.21.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.21.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.21.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.21.mlp.gate":[8,64,[512,640]],"language_model.model.layers.21.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.21.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.21.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.21.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.21.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.20.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.20.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.20.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.20.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.20.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.20.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.20.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.20.mlp.gate":[8,64,[512,640]],"language_model.model.layers.20.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.20.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.20.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.20.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.20.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.19.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.19.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.19.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.19.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.19.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.19.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.19.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.19.mlp.gate":[8,64,[512,640]],"language_model.model.layers.19.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.19.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.19.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.19.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.19.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.18.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.18.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.18.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.18.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.18.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.18.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.18.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.18.mlp.gate":[8,64,[512,640]],"language_model.model.layers.18.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.18.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.18.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.18.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.18.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.17.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.17.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.17.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.17.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.17.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.17.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.17.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.17.mlp.gate":[8,64,[512,640]],"language_model.model.layers.17.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.17.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.17.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.17.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.17.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.16.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.16.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.16.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.16.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.16.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.16.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.16.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.16.mlp.gate":[8,64,[512,640]],"language_model.model.layers.16.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.16.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.16.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.16.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.16.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.15.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.15.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.15.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.15.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.15.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.15.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.15.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.15.mlp.gate":[8,64,[512,640]],"language_model.model.layers.15.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.15.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.15.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.15.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.15.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.14.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.14.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.14.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.14.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.14.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.14.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.14.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.14.mlp.gate":[8,64,[512,640]],"language_model.model.layers.14.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.14.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.14.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.14.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.14.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.13.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.13.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.13.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.13.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.13.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.13.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.13.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.13.mlp.gate":[8,64,[512,640]],"language_model.model.layers.13.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.13.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.13.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.13.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.13.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.12.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.12.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.12.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.12.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.12.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.12.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.12.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.12.mlp.gate":[8,64,[512,640]],"language_model.model.layers.12.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.12.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.12.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.12.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.12.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.11.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.11.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.11.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.11.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.11.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.11.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.11.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.11.mlp.gate":[8,64,[512,640]],"language_model.model.layers.11.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.11.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.11.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.11.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.11.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.10.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.10.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.10.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.10.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.10.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.10.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.10.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.10.mlp.gate":[8,64,[512,640]],"language_model.model.layers.10.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.10.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.10.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.10.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.10.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.9.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.9.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.9.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.9.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.9.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.9.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.9.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.9.mlp.gate":[8,64,[512,640]],"language_model.model.layers.9.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.9.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.9.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.9.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.9.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.8.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.8.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.8.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.8.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.8.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.8.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.8.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.8.mlp.gate":[8,64,[512,640]],"language_model.model.layers.8.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.8.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.8.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.8.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.8.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.7.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.7.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.7.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.7.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.7.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.7.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.7.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.7.mlp.gate":[8,64,[512,640]],"language_model.model.layers.7.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.7.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.7.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.7.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.7.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.6.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.6.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.6.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.6.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.6.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.6.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.6.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.6.mlp.gate":[8,64,[512,640]],"language_model.model.layers.6.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.6.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.6.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.6.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.6.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.5.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.5.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.5.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.5.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.5.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.5.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.5.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.5.mlp.gate":[8,64,[512,640]],"language_model.model.layers.5.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.5.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.5.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.5.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.5.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.4.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.4.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.4.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.4.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.4.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.4.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.4.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.4.mlp.gate":[8,64,[512,640]],"language_model.model.layers.4.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.4.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.4.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.4.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.4.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.3.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.3.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.3.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.3.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.3.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.3.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.3.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.3.mlp.gate":[8,64,[512,640]],"language_model.model.layers.3.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.3.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.3.self_attn.v_proj":[4,64,[512,320]],"language_model.model.layers.3.self_attn.k_proj":[4,64,[512,320]],"language_model.model.layers.3.self_attn.q_proj":[4,64,[12288,320]],"language_model.model.layers.2.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.2.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.2.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.2.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.2.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.2.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.2.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.2.mlp.gate":[8,64,[512,640]],"language_model.model.layers.2.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.2.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.2.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.2.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.2.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.1.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.1.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.1.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.1.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.1.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.1.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.1.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.1.mlp.gate":[8,64,[512,640]],"language_model.model.layers.1.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.1.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.1.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.1.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.1.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.layers.0.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.0.mlp.shared_expert.up_proj":[4,64,[640,320]],"language_model.model.layers.0.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.0.mlp.shared_expert.gate_proj":[4,64,[640,320]],"language_model.model.layers.0.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.0.mlp.switch_mlp.up_proj":[4,64,[512,640,320]],"language_model.model.layers.0.mlp.switch_mlp.gate_proj":[4,64,[512,640,320]],"language_model.model.layers.0.mlp.gate":[8,64,[512,640]],"language_model.model.layers.0.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.0.linear_attn.in_proj_a":[4,64,[48,320]],"language_model.model.layers.0.linear_attn.in_proj_b":[4,64,[48,320]],"language_model.model.layers.0.linear_attn.in_proj_z":[4,64,[6144,320]],"language_model.model.layers.0.linear_attn.in_proj_qkv":[4,64,[10240,320]],"language_model.model.embed_tokens":[4,64,[248320,320]]},"norms":{"mtp.pre_fc_norm_embedding.weight":"fd600a4b5af7497016cfc8f4a6d9a71b06ab64ba9ead2a035ce088c51d008a51","mtp.pre_fc_norm_hidden.weight":"c5f0fb8420ee5fa3494090d100a400a670f3540df4a11ab9a76304d07796ffdf"},"ple":[1],"linear":[0,1,2,4,5,6,8,9,10,12,13,14,16,17,18,20,21,22,24,25,26,28,29,30,32,33,34,36,37,38,40,41,42,44,45,46]}
{"mask":7,"mtp":true,"parameter_count":1840,"metadata_sha256":"6d4f062d5baf0adf41b57fb242d978d17eefebcc0d428fa7a70c040e6bad960c","quantized":{"mtp.layers.0.mlp.shared_expert_gate":[4,64,[1,320]],"mtp.layers.0.mlp.shared_expert.up_proj":[4,64,[640,320]],"mtp.layers.0.mlp.shared_expert.down_proj":[4,64,[2560,80]],"mtp.layers.0.mlp.shared_expert.gate_proj":[4,64,[640,320]],"mtp.layers.0.mlp.switch_mlp.down_proj":[4,32,[512,2560,80]],"mtp.layers.0.mlp.switch_mlp.up_proj":[4,32,[512,640,320]],"mtp.layers.0.mlp.switch_mlp.gate_proj":[4,32,[512,640,320]],"mtp.layers.0.mlp.gate":[8,64,[512,640]],"mtp.layers.0.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"mtp.layers.0.self_attn.o_proj":[4,64,[2560,768]],"mtp.layers.0.self_attn.v_proj":[4,64,[512,320]],"mtp.layers.0.self_attn.k_proj":[4,64,[512,320]],"mtp.layers.0.self_attn.q_proj":[4,64,[12288,320]],"language_model.lm_head":[4,64,[248320,320]],"language_model.model.layers.47.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.47.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.47.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.47.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.47.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.47.mlp.gate":[8,64,[512,640]],"language_model.model.layers.47.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.47.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.47.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.46.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.46.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.46.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.46.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.46.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.46.mlp.gate":[8,64,[512,640]],"language_model.model.layers.46.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.46.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.45.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.45.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.45.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.45.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.45.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.45.mlp.gate":[8,64,[512,640]],"language_model.model.layers.45.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.45.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.44.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.44.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.44.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.44.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.44.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.44.mlp.gate":[8,64,[512,640]],"language_model.model.layers.44.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.44.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.43.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.43.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.43.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.43.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.43.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.43.mlp.gate":[8,64,[512,640]],"language_model.model.layers.43.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.43.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.43.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.42.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.42.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.42.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.42.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.42.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.42.mlp.gate":[8,64,[512,640]],"language_model.model.layers.42.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.42.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.41.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.41.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.41.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.41.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.41.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.41.mlp.gate":[8,64,[512,640]],"language_model.model.layers.41.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.41.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.40.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.40.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.40.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.40.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.40.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.40.mlp.gate":[8,64,[512,640]],"language_model.model.layers.40.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.40.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.39.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.39.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.39.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.39.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.39.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.39.mlp.gate":[8,64,[512,640]],"language_model.model.layers.39.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.39.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.39.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.38.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.38.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.38.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.38.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.38.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.38.mlp.gate":[8,64,[512,640]],"language_model.model.layers.38.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.38.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.37.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.37.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.37.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.37.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.37.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.37.mlp.gate":[8,64,[512,640]],"language_model.model.layers.37.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.37.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.36.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.36.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.36.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.36.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.36.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.36.mlp.gate":[8,64,[512,640]],"language_model.model.layers.36.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.36.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.35.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.35.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.35.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.35.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.35.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.35.mlp.gate":[8,64,[512,640]],"language_model.model.layers.35.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.35.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.35.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.34.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.34.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.34.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.34.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.34.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.34.mlp.gate":[8,64,[512,640]],"language_model.model.layers.34.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.34.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.33.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.33.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.33.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.33.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.33.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.33.mlp.gate":[8,64,[512,640]],"language_model.model.layers.33.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.33.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.32.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.32.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.32.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.32.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.32.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.32.mlp.gate":[8,64,[512,640]],"language_model.model.layers.32.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.32.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.31.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.31.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.31.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.31.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.31.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.31.mlp.gate":[8,64,[512,640]],"language_model.model.layers.31.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.31.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.31.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.30.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.30.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.30.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.30.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.30.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.30.mlp.gate":[8,64,[512,640]],"language_model.model.layers.30.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.30.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.29.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.29.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.29.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.29.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.29.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.29.mlp.gate":[8,64,[512,640]],"language_model.model.layers.29.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.29.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.28.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.28.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.28.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.28.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.28.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.28.mlp.gate":[8,64,[512,640]],"language_model.model.layers.28.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.28.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.27.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.27.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.27.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.27.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.27.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.27.mlp.gate":[8,64,[512,640]],"language_model.model.layers.27.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.27.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.27.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.26.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.26.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.26.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.26.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.26.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.26.mlp.gate":[8,64,[512,640]],"language_model.model.layers.26.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.26.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.25.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.25.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.25.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.25.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.25.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.25.mlp.gate":[8,64,[512,640]],"language_model.model.layers.25.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.25.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.24.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.24.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.24.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.24.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.24.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.24.mlp.gate":[8,64,[512,640]],"language_model.model.layers.24.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.24.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.23.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.23.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.23.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.23.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.23.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.23.mlp.gate":[8,64,[512,640]],"language_model.model.layers.23.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.23.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.23.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.22.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.22.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.22.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.22.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.22.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.22.mlp.gate":[8,64,[512,640]],"language_model.model.layers.22.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.22.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.21.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.21.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.21.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.21.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.21.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.21.mlp.gate":[8,64,[512,640]],"language_model.model.layers.21.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.21.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.20.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.20.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.20.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.20.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.20.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.20.mlp.gate":[8,64,[512,640]],"language_model.model.layers.20.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.20.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.19.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.19.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.19.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.19.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.19.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.19.mlp.gate":[8,64,[512,640]],"language_model.model.layers.19.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.19.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.19.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.18.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.18.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.18.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.18.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.18.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.18.mlp.gate":[8,64,[512,640]],"language_model.model.layers.18.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.18.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.17.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.17.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.17.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.17.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.17.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.17.mlp.gate":[8,64,[512,640]],"language_model.model.layers.17.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.17.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.16.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.16.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.16.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.16.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.16.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.16.mlp.gate":[8,64,[512,640]],"language_model.model.layers.16.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.16.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.15.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.15.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.15.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.15.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.15.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.15.mlp.gate":[8,64,[512,640]],"language_model.model.layers.15.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.15.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.15.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.14.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.14.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.14.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.14.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.14.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.14.mlp.gate":[8,64,[512,640]],"language_model.model.layers.14.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.14.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.13.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.13.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.13.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.13.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.13.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.13.mlp.gate":[8,64,[512,640]],"language_model.model.layers.13.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.13.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.12.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.12.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.12.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.12.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.12.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.12.mlp.gate":[8,64,[512,640]],"language_model.model.layers.12.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.12.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.11.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.11.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.11.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.11.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.11.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.11.mlp.gate":[8,64,[512,640]],"language_model.model.layers.11.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.11.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.11.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.10.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.10.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.10.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.10.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.10.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.10.mlp.gate":[8,64,[512,640]],"language_model.model.layers.10.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.10.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.9.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.9.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.9.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.9.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.9.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.9.mlp.gate":[8,64,[512,640]],"language_model.model.layers.9.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.9.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.8.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.8.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.8.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.8.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.8.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.8.mlp.gate":[8,64,[512,640]],"language_model.model.layers.8.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.8.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.7.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.7.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.7.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.7.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.7.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.7.mlp.gate":[8,64,[512,640]],"language_model.model.layers.7.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.7.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.7.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.6.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.6.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.6.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.6.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.6.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.6.mlp.gate":[8,64,[512,640]],"language_model.model.layers.6.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.6.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.5.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.5.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.5.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.5.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.5.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.5.mlp.gate":[8,64,[512,640]],"language_model.model.layers.5.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.5.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.4.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.4.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.4.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.4.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.4.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.4.mlp.gate":[8,64,[512,640]],"language_model.model.layers.4.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.4.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.3.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.3.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.3.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.3.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.3.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.3.mlp.gate":[8,64,[512,640]],"language_model.model.layers.3.self_attn.qkv_fused":[4,64,[13312,320]],"language_model.model.layers.3.self_attn.indexer.index_qk_proj":[8,64,[640,640]],"language_model.model.layers.3.self_attn.o_proj":[4,64,[2560,768]],"language_model.model.layers.2.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.2.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.2.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.2.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.2.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.2.mlp.gate":[8,64,[512,640]],"language_model.model.layers.2.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.2.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.1.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.1.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.1.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.1.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.1.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.1.mlp.gate":[8,64,[512,640]],"language_model.model.layers.1.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.1.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.layers.0.mlp.shared_expert_gate":[4,64,[1,320]],"language_model.model.layers.0.mlp.shared_expert.gu":[4,64,[1280,320]],"language_model.model.layers.0.mlp.shared_expert.down_proj":[4,64,[2560,80]],"language_model.model.layers.0.mlp.switch_mlp.gu":[4,64,[512,1280,320]],"language_model.model.layers.0.mlp.switch_mlp.down_proj":[4,64,[512,2560,80]],"language_model.model.layers.0.mlp.gate":[8,64,[512,640]],"language_model.model.layers.0.linear_attn.in_proj_fused":[4,64,[16480,320]],"language_model.model.layers.0.linear_attn.out_proj":[4,64,[2560,768]],"language_model.model.embed_tokens":[4,64,[248320,320]]},"norms":{"mtp.pre_fc_norm_embedding.weight":"fd600a4b5af7497016cfc8f4a6d9a71b06ab64ba9ead2a035ce088c51d008a51","mtp.pre_fc_norm_hidden.weight":"c5f0fb8420ee5fa3494090d100a400a670f3540df4a11ab9a76304d07796ffdf"},"ple":[1],"linear":[0,1,2,4,5,6,8,9,10,12,13,14,16,17,18,20,21,22,24,25,26,28,29,30,32,33,34,36,37,38,40,41,42,44,45,46]}