File size: 137,410 Bytes
61fbab4 | 1 | {"format": "freetoken_weight", "version": 1, "align": 4096, "shard_limit": 8589934592, "total_bytes": 22898896896, "tensors": [{"name": "model.embed_tokens.weight", "kind": "weight", "dtype": "bfloat16", "shape": [248320, 2048], "global_off": 0, "nbytes": 1017118720}, {"name": "lm_head.weight", "kind": "weight", "dtype": "bfloat16", "shape": [248320, 2048], "global_off": 1017118720, "nbytes": 1017118720}, {"name": "model.layers.0.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2034237440, "nbytes": 4096}, {"name": "model.layers.0.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2034241536, "nbytes": 64}, {"name": "model.layers.0.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2034245632, "nbytes": 65536}, {"name": "model.layers.0.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2034311168, "nbytes": 64}, {"name": "model.layers.0.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2034315264, "nbytes": 50593792}, {"name": "model.layers.0.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2084909056, "nbytes": 256}, {"name": "model.layers.0.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2084913152, "nbytes": 16777216}, {"name": "model.layers.0.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2101690368, "nbytes": 1048576}, {"name": "model.layers.0.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2102738944, "nbytes": 524288}, {"name": "model.layers.0.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2103263232, "nbytes": 65536}, {"name": "model.layers.0.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2103328768, "nbytes": 4096}, {"name": "model.layers.0.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2103332864, "nbytes": 1048576}, {"name": "model.layers.0.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2104381440, "nbytes": 131072}, {"name": "model.layers.0.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2104512512, "nbytes": 2048}, {"name": "model.layers.0.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2104516608, "nbytes": 4096}, {"name": "model.layers.0.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2104520704, "nbytes": 4096}, {"name": "model.layers.1.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2104524800, "nbytes": 4096}, {"name": "model.layers.1.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2104528896, "nbytes": 64}, {"name": "model.layers.1.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2104532992, "nbytes": 65536}, {"name": "model.layers.1.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2104598528, "nbytes": 64}, {"name": "model.layers.1.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2104602624, "nbytes": 50593792}, {"name": "model.layers.1.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2155196416, "nbytes": 256}, {"name": "model.layers.1.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2155200512, "nbytes": 16777216}, {"name": "model.layers.1.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2171977728, "nbytes": 1048576}, {"name": "model.layers.1.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2173026304, "nbytes": 524288}, {"name": "model.layers.1.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2173550592, "nbytes": 65536}, {"name": "model.layers.1.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2173616128, "nbytes": 4096}, {"name": "model.layers.1.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2173620224, "nbytes": 1048576}, {"name": "model.layers.1.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2174668800, "nbytes": 131072}, {"name": "model.layers.1.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2174799872, "nbytes": 2048}, {"name": "model.layers.1.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2174803968, "nbytes": 4096}, {"name": "model.layers.1.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2174808064, "nbytes": 4096}, {"name": "model.layers.10.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2174812160, "nbytes": 4096}, {"name": "model.layers.10.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2174816256, "nbytes": 64}, {"name": "model.layers.10.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2174820352, "nbytes": 65536}, {"name": "model.layers.10.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2174885888, "nbytes": 64}, {"name": "model.layers.10.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2174889984, "nbytes": 50593792}, {"name": "model.layers.10.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2225483776, "nbytes": 256}, {"name": "model.layers.10.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2225487872, "nbytes": 16777216}, {"name": "model.layers.10.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2242265088, "nbytes": 1048576}, {"name": "model.layers.10.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2243313664, "nbytes": 524288}, {"name": "model.layers.10.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2243837952, "nbytes": 65536}, {"name": "model.layers.10.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2243903488, "nbytes": 4096}, {"name": "model.layers.10.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2243907584, "nbytes": 1048576}, {"name": "model.layers.10.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2244956160, "nbytes": 131072}, {"name": "model.layers.10.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2245087232, "nbytes": 2048}, {"name": "model.layers.10.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2245091328, "nbytes": 4096}, {"name": "model.layers.10.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2245095424, "nbytes": 4096}, {"name": "model.layers.11.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2245099520, "nbytes": 4096}, {"name": "model.layers.11.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2245103616, "nbytes": 1048576}, {"name": "model.layers.11.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2246152192, "nbytes": 524288}, {"name": "model.layers.11.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2246676480, "nbytes": 65536}, {"name": "model.layers.11.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2246742016, "nbytes": 4096}, {"name": "model.layers.11.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2246746112, "nbytes": 1048576}, {"name": "model.layers.11.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2247794688, "nbytes": 131072}, {"name": "model.layers.11.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2247925760, "nbytes": 2048}, {"name": "model.layers.11.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2247929856, "nbytes": 4096}, {"name": "model.layers.11.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2247933952, "nbytes": 4096}, {"name": "model.layers.11.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 2247938048, "nbytes": 512}, {"name": "model.layers.11.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2247942144, "nbytes": 16777216}, {"name": "model.layers.11.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 2264719360, "nbytes": 512}, {"name": "model.layers.11.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 2264723456, "nbytes": 37748736}, {"name": "model.layers.12.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2302472192, "nbytes": 4096}, {"name": "model.layers.12.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2302476288, "nbytes": 64}, {"name": "model.layers.12.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2302480384, "nbytes": 65536}, {"name": "model.layers.12.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2302545920, "nbytes": 64}, {"name": "model.layers.12.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2302550016, "nbytes": 50593792}, {"name": "model.layers.12.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2353143808, "nbytes": 256}, {"name": "model.layers.12.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2353147904, "nbytes": 16777216}, {"name": "model.layers.12.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2369925120, "nbytes": 1048576}, {"name": "model.layers.12.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2370973696, "nbytes": 524288}, {"name": "model.layers.12.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2371497984, "nbytes": 65536}, {"name": "model.layers.12.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2371563520, "nbytes": 4096}, {"name": "model.layers.12.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2371567616, "nbytes": 1048576}, {"name": "model.layers.12.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2372616192, "nbytes": 131072}, {"name": "model.layers.12.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2372747264, "nbytes": 2048}, {"name": "model.layers.12.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2372751360, "nbytes": 4096}, {"name": "model.layers.12.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2372755456, "nbytes": 4096}, {"name": "model.layers.13.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2372759552, "nbytes": 4096}, {"name": "model.layers.13.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2372763648, "nbytes": 64}, {"name": "model.layers.13.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2372767744, "nbytes": 65536}, {"name": "model.layers.13.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2372833280, "nbytes": 64}, {"name": "model.layers.13.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2372837376, "nbytes": 50593792}, {"name": "model.layers.13.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2423431168, "nbytes": 256}, {"name": "model.layers.13.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2423435264, "nbytes": 16777216}, {"name": "model.layers.13.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2440212480, "nbytes": 1048576}, {"name": "model.layers.13.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2441261056, "nbytes": 524288}, {"name": "model.layers.13.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2441785344, "nbytes": 65536}, {"name": "model.layers.13.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2441850880, "nbytes": 4096}, {"name": "model.layers.13.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2441854976, "nbytes": 1048576}, {"name": "model.layers.13.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2442903552, "nbytes": 131072}, {"name": "model.layers.13.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2443034624, "nbytes": 2048}, {"name": "model.layers.13.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2443038720, "nbytes": 4096}, {"name": "model.layers.13.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2443042816, "nbytes": 4096}, {"name": "model.layers.14.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2443046912, "nbytes": 4096}, {"name": "model.layers.14.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2443051008, "nbytes": 64}, {"name": "model.layers.14.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2443055104, "nbytes": 65536}, {"name": "model.layers.14.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2443120640, "nbytes": 64}, {"name": "model.layers.14.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2443124736, "nbytes": 50593792}, {"name": "model.layers.14.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2493718528, "nbytes": 256}, {"name": "model.layers.14.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2493722624, "nbytes": 16777216}, {"name": "model.layers.14.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2510499840, "nbytes": 1048576}, {"name": "model.layers.14.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2511548416, "nbytes": 524288}, {"name": "model.layers.14.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2512072704, "nbytes": 65536}, {"name": "model.layers.14.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2512138240, "nbytes": 4096}, {"name": "model.layers.14.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2512142336, "nbytes": 1048576}, {"name": "model.layers.14.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2513190912, "nbytes": 131072}, {"name": "model.layers.14.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2513321984, "nbytes": 2048}, {"name": "model.layers.14.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2513326080, "nbytes": 4096}, {"name": "model.layers.14.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2513330176, "nbytes": 4096}, {"name": "model.layers.15.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2513334272, "nbytes": 4096}, {"name": "model.layers.15.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2513338368, "nbytes": 1048576}, {"name": "model.layers.15.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2514386944, "nbytes": 524288}, {"name": "model.layers.15.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2514911232, "nbytes": 65536}, {"name": "model.layers.15.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2514976768, "nbytes": 4096}, {"name": "model.layers.15.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2514980864, "nbytes": 1048576}, {"name": "model.layers.15.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2516029440, "nbytes": 131072}, {"name": "model.layers.15.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2516160512, "nbytes": 2048}, {"name": "model.layers.15.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2516164608, "nbytes": 4096}, {"name": "model.layers.15.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2516168704, "nbytes": 4096}, {"name": "model.layers.15.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 2516172800, "nbytes": 512}, {"name": "model.layers.15.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2516176896, "nbytes": 16777216}, {"name": "model.layers.15.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 2532954112, "nbytes": 512}, {"name": "model.layers.15.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 2532958208, "nbytes": 37748736}, {"name": "model.layers.16.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2570706944, "nbytes": 4096}, {"name": "model.layers.16.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2570711040, "nbytes": 64}, {"name": "model.layers.16.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2570715136, "nbytes": 65536}, {"name": "model.layers.16.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2570780672, "nbytes": 64}, {"name": "model.layers.16.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2570784768, "nbytes": 50593792}, {"name": "model.layers.16.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2621378560, "nbytes": 256}, {"name": "model.layers.16.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2621382656, "nbytes": 16777216}, {"name": "model.layers.16.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2638159872, "nbytes": 1048576}, {"name": "model.layers.16.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2639208448, "nbytes": 524288}, {"name": "model.layers.16.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2639732736, "nbytes": 65536}, {"name": "model.layers.16.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2639798272, "nbytes": 4096}, {"name": "model.layers.16.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2639802368, "nbytes": 1048576}, {"name": "model.layers.16.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2640850944, "nbytes": 131072}, {"name": "model.layers.16.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2640982016, "nbytes": 2048}, {"name": "model.layers.16.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2640986112, "nbytes": 4096}, {"name": "model.layers.16.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2640990208, "nbytes": 4096}, {"name": "model.layers.17.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2640994304, "nbytes": 4096}, {"name": "model.layers.17.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2640998400, "nbytes": 64}, {"name": "model.layers.17.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2641002496, "nbytes": 65536}, {"name": "model.layers.17.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2641068032, "nbytes": 64}, {"name": "model.layers.17.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2641072128, "nbytes": 50593792}, {"name": "model.layers.17.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2691665920, "nbytes": 256}, {"name": "model.layers.17.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2691670016, "nbytes": 16777216}, {"name": "model.layers.17.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2708447232, "nbytes": 1048576}, {"name": "model.layers.17.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2709495808, "nbytes": 524288}, {"name": "model.layers.17.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2710020096, "nbytes": 65536}, {"name": "model.layers.17.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2710085632, "nbytes": 4096}, {"name": "model.layers.17.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2710089728, "nbytes": 1048576}, {"name": "model.layers.17.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2711138304, "nbytes": 131072}, {"name": "model.layers.17.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2711269376, "nbytes": 2048}, {"name": "model.layers.17.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2711273472, "nbytes": 4096}, {"name": "model.layers.17.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2711277568, "nbytes": 4096}, {"name": "model.layers.18.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2711281664, "nbytes": 4096}, {"name": "model.layers.18.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2711285760, "nbytes": 64}, {"name": "model.layers.18.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2711289856, "nbytes": 65536}, {"name": "model.layers.18.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2711355392, "nbytes": 64}, {"name": "model.layers.18.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2711359488, "nbytes": 50593792}, {"name": "model.layers.18.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2761953280, "nbytes": 256}, {"name": "model.layers.18.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2761957376, "nbytes": 16777216}, {"name": "model.layers.18.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2778734592, "nbytes": 1048576}, {"name": "model.layers.18.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2779783168, "nbytes": 524288}, {"name": "model.layers.18.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2780307456, "nbytes": 65536}, {"name": "model.layers.18.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2780372992, "nbytes": 4096}, {"name": "model.layers.18.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2780377088, "nbytes": 1048576}, {"name": "model.layers.18.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2781425664, "nbytes": 131072}, {"name": "model.layers.18.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2781556736, "nbytes": 2048}, {"name": "model.layers.18.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2781560832, "nbytes": 4096}, {"name": "model.layers.18.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2781564928, "nbytes": 4096}, {"name": "model.layers.19.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2781569024, "nbytes": 4096}, {"name": "model.layers.19.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2781573120, "nbytes": 1048576}, {"name": "model.layers.19.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2782621696, "nbytes": 524288}, {"name": "model.layers.19.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2783145984, "nbytes": 65536}, {"name": "model.layers.19.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2783211520, "nbytes": 4096}, {"name": "model.layers.19.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2783215616, "nbytes": 1048576}, {"name": "model.layers.19.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2784264192, "nbytes": 131072}, {"name": "model.layers.19.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2784395264, "nbytes": 2048}, {"name": "model.layers.19.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2784399360, "nbytes": 4096}, {"name": "model.layers.19.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2784403456, "nbytes": 4096}, {"name": "model.layers.19.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 2784407552, "nbytes": 512}, {"name": "model.layers.19.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2784411648, "nbytes": 16777216}, {"name": "model.layers.19.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 2801188864, "nbytes": 512}, {"name": "model.layers.19.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 2801192960, "nbytes": 37748736}, {"name": "model.layers.2.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2838941696, "nbytes": 4096}, {"name": "model.layers.2.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2838945792, "nbytes": 64}, {"name": "model.layers.2.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2838949888, "nbytes": 65536}, {"name": "model.layers.2.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2839015424, "nbytes": 64}, {"name": "model.layers.2.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2839019520, "nbytes": 50593792}, {"name": "model.layers.2.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2889613312, "nbytes": 256}, {"name": "model.layers.2.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2889617408, "nbytes": 16777216}, {"name": "model.layers.2.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2906394624, "nbytes": 1048576}, {"name": "model.layers.2.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2907443200, "nbytes": 524288}, {"name": "model.layers.2.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2907967488, "nbytes": 65536}, {"name": "model.layers.2.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2908033024, "nbytes": 4096}, {"name": "model.layers.2.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2908037120, "nbytes": 1048576}, {"name": "model.layers.2.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2909085696, "nbytes": 131072}, {"name": "model.layers.2.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2909216768, "nbytes": 2048}, {"name": "model.layers.2.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2909220864, "nbytes": 4096}, {"name": "model.layers.2.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2909224960, "nbytes": 4096}, {"name": "model.layers.20.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2909229056, "nbytes": 4096}, {"name": "model.layers.20.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2909233152, "nbytes": 64}, {"name": "model.layers.20.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2909237248, "nbytes": 65536}, {"name": "model.layers.20.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2909302784, "nbytes": 64}, {"name": "model.layers.20.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2909306880, "nbytes": 50593792}, {"name": "model.layers.20.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 2959900672, "nbytes": 256}, {"name": "model.layers.20.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 2959904768, "nbytes": 16777216}, {"name": "model.layers.20.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 2976681984, "nbytes": 1048576}, {"name": "model.layers.20.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 2977730560, "nbytes": 524288}, {"name": "model.layers.20.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 2978254848, "nbytes": 65536}, {"name": "model.layers.20.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 2978320384, "nbytes": 4096}, {"name": "model.layers.20.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 2978324480, "nbytes": 1048576}, {"name": "model.layers.20.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 2979373056, "nbytes": 131072}, {"name": "model.layers.20.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 2979504128, "nbytes": 2048}, {"name": "model.layers.20.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 2979508224, "nbytes": 4096}, {"name": "model.layers.20.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2979512320, "nbytes": 4096}, {"name": "model.layers.21.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 2979516416, "nbytes": 4096}, {"name": "model.layers.21.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2979520512, "nbytes": 64}, {"name": "model.layers.21.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 2979524608, "nbytes": 65536}, {"name": "model.layers.21.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 2979590144, "nbytes": 64}, {"name": "model.layers.21.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 2979594240, "nbytes": 50593792}, {"name": "model.layers.21.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3030188032, "nbytes": 256}, {"name": "model.layers.21.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3030192128, "nbytes": 16777216}, {"name": "model.layers.21.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3046969344, "nbytes": 1048576}, {"name": "model.layers.21.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3048017920, "nbytes": 524288}, {"name": "model.layers.21.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3048542208, "nbytes": 65536}, {"name": "model.layers.21.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3048607744, "nbytes": 4096}, {"name": "model.layers.21.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3048611840, "nbytes": 1048576}, {"name": "model.layers.21.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3049660416, "nbytes": 131072}, {"name": "model.layers.21.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3049791488, "nbytes": 2048}, {"name": "model.layers.21.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3049795584, "nbytes": 4096}, {"name": "model.layers.21.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3049799680, "nbytes": 4096}, {"name": "model.layers.22.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3049803776, "nbytes": 4096}, {"name": "model.layers.22.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3049807872, "nbytes": 64}, {"name": "model.layers.22.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3049811968, "nbytes": 65536}, {"name": "model.layers.22.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3049877504, "nbytes": 64}, {"name": "model.layers.22.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3049881600, "nbytes": 50593792}, {"name": "model.layers.22.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3100475392, "nbytes": 256}, {"name": "model.layers.22.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3100479488, "nbytes": 16777216}, {"name": "model.layers.22.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3117256704, "nbytes": 1048576}, {"name": "model.layers.22.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3118305280, "nbytes": 524288}, {"name": "model.layers.22.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3118829568, "nbytes": 65536}, {"name": "model.layers.22.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3118895104, "nbytes": 4096}, {"name": "model.layers.22.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3118899200, "nbytes": 1048576}, {"name": "model.layers.22.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3119947776, "nbytes": 131072}, {"name": "model.layers.22.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3120078848, "nbytes": 2048}, {"name": "model.layers.22.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3120082944, "nbytes": 4096}, {"name": "model.layers.22.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3120087040, "nbytes": 4096}, {"name": "model.layers.23.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3120091136, "nbytes": 4096}, {"name": "model.layers.23.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3120095232, "nbytes": 1048576}, {"name": "model.layers.23.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3121143808, "nbytes": 524288}, {"name": "model.layers.23.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3121668096, "nbytes": 65536}, {"name": "model.layers.23.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3121733632, "nbytes": 4096}, {"name": "model.layers.23.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3121737728, "nbytes": 1048576}, {"name": "model.layers.23.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3122786304, "nbytes": 131072}, {"name": "model.layers.23.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3122917376, "nbytes": 2048}, {"name": "model.layers.23.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3122921472, "nbytes": 4096}, {"name": "model.layers.23.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3122925568, "nbytes": 4096}, {"name": "model.layers.23.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3122929664, "nbytes": 512}, {"name": "model.layers.23.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3122933760, "nbytes": 16777216}, {"name": "model.layers.23.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3139710976, "nbytes": 512}, {"name": "model.layers.23.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 3139715072, "nbytes": 37748736}, {"name": "model.layers.24.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3177463808, "nbytes": 4096}, {"name": "model.layers.24.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3177467904, "nbytes": 64}, {"name": "model.layers.24.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3177472000, "nbytes": 65536}, {"name": "model.layers.24.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3177537536, "nbytes": 64}, {"name": "model.layers.24.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3177541632, "nbytes": 50593792}, {"name": "model.layers.24.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3228135424, "nbytes": 256}, {"name": "model.layers.24.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3228139520, "nbytes": 16777216}, {"name": "model.layers.24.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3244916736, "nbytes": 1048576}, {"name": "model.layers.24.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3245965312, "nbytes": 524288}, {"name": "model.layers.24.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3246489600, "nbytes": 65536}, {"name": "model.layers.24.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3246555136, "nbytes": 4096}, {"name": "model.layers.24.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3246559232, "nbytes": 1048576}, {"name": "model.layers.24.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3247607808, "nbytes": 131072}, {"name": "model.layers.24.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3247738880, "nbytes": 2048}, {"name": "model.layers.24.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3247742976, "nbytes": 4096}, {"name": "model.layers.24.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3247747072, "nbytes": 4096}, {"name": "model.layers.25.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3247751168, "nbytes": 4096}, {"name": "model.layers.25.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3247755264, "nbytes": 64}, {"name": "model.layers.25.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3247759360, "nbytes": 65536}, {"name": "model.layers.25.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3247824896, "nbytes": 64}, {"name": "model.layers.25.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3247828992, "nbytes": 50593792}, {"name": "model.layers.25.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3298422784, "nbytes": 256}, {"name": "model.layers.25.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3298426880, "nbytes": 16777216}, {"name": "model.layers.25.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3315204096, "nbytes": 1048576}, {"name": "model.layers.25.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3316252672, "nbytes": 524288}, {"name": "model.layers.25.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3316776960, "nbytes": 65536}, {"name": "model.layers.25.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3316842496, "nbytes": 4096}, {"name": "model.layers.25.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3316846592, "nbytes": 1048576}, {"name": "model.layers.25.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3317895168, "nbytes": 131072}, {"name": "model.layers.25.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3318026240, "nbytes": 2048}, {"name": "model.layers.25.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3318030336, "nbytes": 4096}, {"name": "model.layers.25.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3318034432, "nbytes": 4096}, {"name": "model.layers.26.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3318038528, "nbytes": 4096}, {"name": "model.layers.26.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3318042624, "nbytes": 64}, {"name": "model.layers.26.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3318046720, "nbytes": 65536}, {"name": "model.layers.26.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3318112256, "nbytes": 64}, {"name": "model.layers.26.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3318116352, "nbytes": 50593792}, {"name": "model.layers.26.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3368710144, "nbytes": 256}, {"name": "model.layers.26.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3368714240, "nbytes": 16777216}, {"name": "model.layers.26.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3385491456, "nbytes": 1048576}, {"name": "model.layers.26.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3386540032, "nbytes": 524288}, {"name": "model.layers.26.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3387064320, "nbytes": 65536}, {"name": "model.layers.26.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3387129856, "nbytes": 4096}, {"name": "model.layers.26.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3387133952, "nbytes": 1048576}, {"name": "model.layers.26.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3388182528, "nbytes": 131072}, {"name": "model.layers.26.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3388313600, "nbytes": 2048}, {"name": "model.layers.26.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3388317696, "nbytes": 4096}, {"name": "model.layers.26.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3388321792, "nbytes": 4096}, {"name": "model.layers.27.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3388325888, "nbytes": 4096}, {"name": "model.layers.27.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3388329984, "nbytes": 1048576}, {"name": "model.layers.27.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3389378560, "nbytes": 524288}, {"name": "model.layers.27.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3389902848, "nbytes": 65536}, {"name": "model.layers.27.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3389968384, "nbytes": 4096}, {"name": "model.layers.27.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3389972480, "nbytes": 1048576}, {"name": "model.layers.27.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3391021056, "nbytes": 131072}, {"name": "model.layers.27.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3391152128, "nbytes": 2048}, {"name": "model.layers.27.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3391156224, "nbytes": 4096}, {"name": "model.layers.27.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3391160320, "nbytes": 4096}, {"name": "model.layers.27.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3391164416, "nbytes": 512}, {"name": "model.layers.27.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3391168512, "nbytes": 16777216}, {"name": "model.layers.27.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3407945728, "nbytes": 512}, {"name": "model.layers.27.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 3407949824, "nbytes": 37748736}, {"name": "model.layers.28.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3445698560, "nbytes": 4096}, {"name": "model.layers.28.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3445702656, "nbytes": 64}, {"name": "model.layers.28.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3445706752, "nbytes": 65536}, {"name": "model.layers.28.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3445772288, "nbytes": 64}, {"name": "model.layers.28.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3445776384, "nbytes": 50593792}, {"name": "model.layers.28.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3496370176, "nbytes": 256}, {"name": "model.layers.28.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3496374272, "nbytes": 16777216}, {"name": "model.layers.28.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3513151488, "nbytes": 1048576}, {"name": "model.layers.28.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3514200064, "nbytes": 524288}, {"name": "model.layers.28.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3514724352, "nbytes": 65536}, {"name": "model.layers.28.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3514789888, "nbytes": 4096}, {"name": "model.layers.28.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3514793984, "nbytes": 1048576}, {"name": "model.layers.28.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3515842560, "nbytes": 131072}, {"name": "model.layers.28.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3515973632, "nbytes": 2048}, {"name": "model.layers.28.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3515977728, "nbytes": 4096}, {"name": "model.layers.28.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3515981824, "nbytes": 4096}, {"name": "model.layers.29.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3515985920, "nbytes": 4096}, {"name": "model.layers.29.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3515990016, "nbytes": 64}, {"name": "model.layers.29.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3515994112, "nbytes": 65536}, {"name": "model.layers.29.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3516059648, "nbytes": 64}, {"name": "model.layers.29.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3516063744, "nbytes": 50593792}, {"name": "model.layers.29.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3566657536, "nbytes": 256}, {"name": "model.layers.29.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3566661632, "nbytes": 16777216}, {"name": "model.layers.29.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3583438848, "nbytes": 1048576}, {"name": "model.layers.29.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3584487424, "nbytes": 524288}, {"name": "model.layers.29.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3585011712, "nbytes": 65536}, {"name": "model.layers.29.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3585077248, "nbytes": 4096}, {"name": "model.layers.29.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3585081344, "nbytes": 1048576}, {"name": "model.layers.29.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3586129920, "nbytes": 131072}, {"name": "model.layers.29.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3586260992, "nbytes": 2048}, {"name": "model.layers.29.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3586265088, "nbytes": 4096}, {"name": "model.layers.29.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3586269184, "nbytes": 4096}, {"name": "model.layers.3.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3586273280, "nbytes": 4096}, {"name": "model.layers.3.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3586277376, "nbytes": 1048576}, {"name": "model.layers.3.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3587325952, "nbytes": 524288}, {"name": "model.layers.3.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3587850240, "nbytes": 65536}, {"name": "model.layers.3.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3587915776, "nbytes": 4096}, {"name": "model.layers.3.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3587919872, "nbytes": 1048576}, {"name": "model.layers.3.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3588968448, "nbytes": 131072}, {"name": "model.layers.3.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3589099520, "nbytes": 2048}, {"name": "model.layers.3.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3589103616, "nbytes": 4096}, {"name": "model.layers.3.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3589107712, "nbytes": 4096}, {"name": "model.layers.3.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3589111808, "nbytes": 512}, {"name": "model.layers.3.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3589115904, "nbytes": 16777216}, {"name": "model.layers.3.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3605893120, "nbytes": 512}, {"name": "model.layers.3.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 3605897216, "nbytes": 37748736}, {"name": "model.layers.30.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3643645952, "nbytes": 4096}, {"name": "model.layers.30.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3643650048, "nbytes": 64}, {"name": "model.layers.30.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3643654144, "nbytes": 65536}, {"name": "model.layers.30.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3643719680, "nbytes": 64}, {"name": "model.layers.30.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3643723776, "nbytes": 50593792}, {"name": "model.layers.30.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3694317568, "nbytes": 256}, {"name": "model.layers.30.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3694321664, "nbytes": 16777216}, {"name": "model.layers.30.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3711098880, "nbytes": 1048576}, {"name": "model.layers.30.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3712147456, "nbytes": 524288}, {"name": "model.layers.30.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3712671744, "nbytes": 65536}, {"name": "model.layers.30.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3712737280, "nbytes": 4096}, {"name": "model.layers.30.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3712741376, "nbytes": 1048576}, {"name": "model.layers.30.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3713789952, "nbytes": 131072}, {"name": "model.layers.30.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3713921024, "nbytes": 2048}, {"name": "model.layers.30.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3713925120, "nbytes": 4096}, {"name": "model.layers.30.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3713929216, "nbytes": 4096}, {"name": "model.layers.31.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3713933312, "nbytes": 4096}, {"name": "model.layers.31.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3713937408, "nbytes": 1048576}, {"name": "model.layers.31.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3714985984, "nbytes": 524288}, {"name": "model.layers.31.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3715510272, "nbytes": 65536}, {"name": "model.layers.31.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3715575808, "nbytes": 4096}, {"name": "model.layers.31.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3715579904, "nbytes": 1048576}, {"name": "model.layers.31.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3716628480, "nbytes": 131072}, {"name": "model.layers.31.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3716759552, "nbytes": 2048}, {"name": "model.layers.31.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3716763648, "nbytes": 4096}, {"name": "model.layers.31.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3716767744, "nbytes": 4096}, {"name": "model.layers.31.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3716771840, "nbytes": 512}, {"name": "model.layers.31.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3716775936, "nbytes": 16777216}, {"name": "model.layers.31.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3733553152, "nbytes": 512}, {"name": "model.layers.31.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 3733557248, "nbytes": 37748736}, {"name": "model.layers.32.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3771305984, "nbytes": 4096}, {"name": "model.layers.32.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3771310080, "nbytes": 64}, {"name": "model.layers.32.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3771314176, "nbytes": 65536}, {"name": "model.layers.32.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3771379712, "nbytes": 64}, {"name": "model.layers.32.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3771383808, "nbytes": 50593792}, {"name": "model.layers.32.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3821977600, "nbytes": 256}, {"name": "model.layers.32.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3821981696, "nbytes": 16777216}, {"name": "model.layers.32.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3838758912, "nbytes": 1048576}, {"name": "model.layers.32.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3839807488, "nbytes": 524288}, {"name": "model.layers.32.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3840331776, "nbytes": 65536}, {"name": "model.layers.32.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3840397312, "nbytes": 4096}, {"name": "model.layers.32.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3840401408, "nbytes": 1048576}, {"name": "model.layers.32.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3841449984, "nbytes": 131072}, {"name": "model.layers.32.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3841581056, "nbytes": 2048}, {"name": "model.layers.32.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3841585152, "nbytes": 4096}, {"name": "model.layers.32.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3841589248, "nbytes": 4096}, {"name": "model.layers.33.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3841593344, "nbytes": 4096}, {"name": "model.layers.33.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3841597440, "nbytes": 64}, {"name": "model.layers.33.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3841601536, "nbytes": 65536}, {"name": "model.layers.33.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3841667072, "nbytes": 64}, {"name": "model.layers.33.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3841671168, "nbytes": 50593792}, {"name": "model.layers.33.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3892264960, "nbytes": 256}, {"name": "model.layers.33.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3892269056, "nbytes": 16777216}, {"name": "model.layers.33.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3909046272, "nbytes": 1048576}, {"name": "model.layers.33.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3910094848, "nbytes": 524288}, {"name": "model.layers.33.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3910619136, "nbytes": 65536}, {"name": "model.layers.33.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3910684672, "nbytes": 4096}, {"name": "model.layers.33.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3910688768, "nbytes": 1048576}, {"name": "model.layers.33.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3911737344, "nbytes": 131072}, {"name": "model.layers.33.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3911868416, "nbytes": 2048}, {"name": "model.layers.33.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3911872512, "nbytes": 4096}, {"name": "model.layers.33.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3911876608, "nbytes": 4096}, {"name": "model.layers.34.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3911880704, "nbytes": 4096}, {"name": "model.layers.34.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3911884800, "nbytes": 64}, {"name": "model.layers.34.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 3911888896, "nbytes": 65536}, {"name": "model.layers.34.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 3911954432, "nbytes": 64}, {"name": "model.layers.34.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 3911958528, "nbytes": 50593792}, {"name": "model.layers.34.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 3962552320, "nbytes": 256}, {"name": "model.layers.34.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3962556416, "nbytes": 16777216}, {"name": "model.layers.34.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3979333632, "nbytes": 1048576}, {"name": "model.layers.34.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3980382208, "nbytes": 524288}, {"name": "model.layers.34.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3980906496, "nbytes": 65536}, {"name": "model.layers.34.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3980972032, "nbytes": 4096}, {"name": "model.layers.34.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3980976128, "nbytes": 1048576}, {"name": "model.layers.34.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3982024704, "nbytes": 131072}, {"name": "model.layers.34.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3982155776, "nbytes": 2048}, {"name": "model.layers.34.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3982159872, "nbytes": 4096}, {"name": "model.layers.34.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3982163968, "nbytes": 4096}, {"name": "model.layers.35.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3982168064, "nbytes": 4096}, {"name": "model.layers.35.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 3982172160, "nbytes": 1048576}, {"name": "model.layers.35.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 3983220736, "nbytes": 524288}, {"name": "model.layers.35.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 3983745024, "nbytes": 65536}, {"name": "model.layers.35.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 3983810560, "nbytes": 4096}, {"name": "model.layers.35.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 3983814656, "nbytes": 1048576}, {"name": "model.layers.35.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 3984863232, "nbytes": 131072}, {"name": "model.layers.35.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 3984994304, "nbytes": 2048}, {"name": "model.layers.35.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 3984998400, "nbytes": 4096}, {"name": "model.layers.35.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 3985002496, "nbytes": 4096}, {"name": "model.layers.35.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 3985006592, "nbytes": 512}, {"name": "model.layers.35.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 3985010688, "nbytes": 16777216}, {"name": "model.layers.35.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 4001787904, "nbytes": 512}, {"name": "model.layers.35.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 4001792000, "nbytes": 37748736}, {"name": "model.layers.36.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4039540736, "nbytes": 4096}, {"name": "model.layers.36.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4039544832, "nbytes": 64}, {"name": "model.layers.36.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4039548928, "nbytes": 65536}, {"name": "model.layers.36.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4039614464, "nbytes": 64}, {"name": "model.layers.36.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4039618560, "nbytes": 50593792}, {"name": "model.layers.36.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4090212352, "nbytes": 256}, {"name": "model.layers.36.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4090216448, "nbytes": 16777216}, {"name": "model.layers.36.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4106993664, "nbytes": 1048576}, {"name": "model.layers.36.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4108042240, "nbytes": 524288}, {"name": "model.layers.36.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4108566528, "nbytes": 65536}, {"name": "model.layers.36.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4108632064, "nbytes": 4096}, {"name": "model.layers.36.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4108636160, "nbytes": 1048576}, {"name": "model.layers.36.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4109684736, "nbytes": 131072}, {"name": "model.layers.36.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4109815808, "nbytes": 2048}, {"name": "model.layers.36.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4109819904, "nbytes": 4096}, {"name": "model.layers.36.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4109824000, "nbytes": 4096}, {"name": "model.layers.37.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4109828096, "nbytes": 4096}, {"name": "model.layers.37.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4109832192, "nbytes": 64}, {"name": "model.layers.37.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4109836288, "nbytes": 65536}, {"name": "model.layers.37.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4109901824, "nbytes": 64}, {"name": "model.layers.37.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4109905920, "nbytes": 50593792}, {"name": "model.layers.37.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4160499712, "nbytes": 256}, {"name": "model.layers.37.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4160503808, "nbytes": 16777216}, {"name": "model.layers.37.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4177281024, "nbytes": 1048576}, {"name": "model.layers.37.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4178329600, "nbytes": 524288}, {"name": "model.layers.37.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4178853888, "nbytes": 65536}, {"name": "model.layers.37.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4178919424, "nbytes": 4096}, {"name": "model.layers.37.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4178923520, "nbytes": 1048576}, {"name": "model.layers.37.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4179972096, "nbytes": 131072}, {"name": "model.layers.37.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4180103168, "nbytes": 2048}, {"name": "model.layers.37.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4180107264, "nbytes": 4096}, {"name": "model.layers.37.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4180111360, "nbytes": 4096}, {"name": "model.layers.38.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4180115456, "nbytes": 4096}, {"name": "model.layers.38.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4180119552, "nbytes": 64}, {"name": "model.layers.38.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4180123648, "nbytes": 65536}, {"name": "model.layers.38.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4180189184, "nbytes": 64}, {"name": "model.layers.38.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4180193280, "nbytes": 50593792}, {"name": "model.layers.38.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4230787072, "nbytes": 256}, {"name": "model.layers.38.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4230791168, "nbytes": 16777216}, {"name": "model.layers.38.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4247568384, "nbytes": 1048576}, {"name": "model.layers.38.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4248616960, "nbytes": 524288}, {"name": "model.layers.38.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4249141248, "nbytes": 65536}, {"name": "model.layers.38.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4249206784, "nbytes": 4096}, {"name": "model.layers.38.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4249210880, "nbytes": 1048576}, {"name": "model.layers.38.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4250259456, "nbytes": 131072}, {"name": "model.layers.38.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4250390528, "nbytes": 2048}, {"name": "model.layers.38.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4250394624, "nbytes": 4096}, {"name": "model.layers.38.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4250398720, "nbytes": 4096}, {"name": "model.layers.39.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4250402816, "nbytes": 4096}, {"name": "model.layers.39.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4250406912, "nbytes": 1048576}, {"name": "model.layers.39.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4251455488, "nbytes": 524288}, {"name": "model.layers.39.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4251979776, "nbytes": 65536}, {"name": "model.layers.39.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4252045312, "nbytes": 4096}, {"name": "model.layers.39.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4252049408, "nbytes": 1048576}, {"name": "model.layers.39.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4253097984, "nbytes": 131072}, {"name": "model.layers.39.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4253229056, "nbytes": 2048}, {"name": "model.layers.39.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4253233152, "nbytes": 4096}, {"name": "model.layers.39.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4253237248, "nbytes": 4096}, {"name": "model.layers.39.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 4253241344, "nbytes": 512}, {"name": "model.layers.39.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4253245440, "nbytes": 16777216}, {"name": "model.layers.39.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 4270022656, "nbytes": 512}, {"name": "model.layers.39.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 4270026752, "nbytes": 37748736}, {"name": "model.layers.4.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4307775488, "nbytes": 4096}, {"name": "model.layers.4.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4307779584, "nbytes": 64}, {"name": "model.layers.4.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4307783680, "nbytes": 65536}, {"name": "model.layers.4.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4307849216, "nbytes": 64}, {"name": "model.layers.4.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4307853312, "nbytes": 50593792}, {"name": "model.layers.4.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4358447104, "nbytes": 256}, {"name": "model.layers.4.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4358451200, "nbytes": 16777216}, {"name": "model.layers.4.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4375228416, "nbytes": 1048576}, {"name": "model.layers.4.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4376276992, "nbytes": 524288}, {"name": "model.layers.4.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4376801280, "nbytes": 65536}, {"name": "model.layers.4.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4376866816, "nbytes": 4096}, {"name": "model.layers.4.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4376870912, "nbytes": 1048576}, {"name": "model.layers.4.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4377919488, "nbytes": 131072}, {"name": "model.layers.4.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4378050560, "nbytes": 2048}, {"name": "model.layers.4.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4378054656, "nbytes": 4096}, {"name": "model.layers.4.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4378058752, "nbytes": 4096}, {"name": "model.layers.5.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4378062848, "nbytes": 4096}, {"name": "model.layers.5.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4378066944, "nbytes": 64}, {"name": "model.layers.5.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4378071040, "nbytes": 65536}, {"name": "model.layers.5.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4378136576, "nbytes": 64}, {"name": "model.layers.5.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4378140672, "nbytes": 50593792}, {"name": "model.layers.5.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4428734464, "nbytes": 256}, {"name": "model.layers.5.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4428738560, "nbytes": 16777216}, {"name": "model.layers.5.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4445515776, "nbytes": 1048576}, {"name": "model.layers.5.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4446564352, "nbytes": 524288}, {"name": "model.layers.5.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4447088640, "nbytes": 65536}, {"name": "model.layers.5.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4447154176, "nbytes": 4096}, {"name": "model.layers.5.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4447158272, "nbytes": 1048576}, {"name": "model.layers.5.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4448206848, "nbytes": 131072}, {"name": "model.layers.5.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4448337920, "nbytes": 2048}, {"name": "model.layers.5.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4448342016, "nbytes": 4096}, {"name": "model.layers.5.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4448346112, "nbytes": 4096}, {"name": "model.layers.6.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4448350208, "nbytes": 4096}, {"name": "model.layers.6.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4448354304, "nbytes": 64}, {"name": "model.layers.6.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4448358400, "nbytes": 65536}, {"name": "model.layers.6.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4448423936, "nbytes": 64}, {"name": "model.layers.6.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4448428032, "nbytes": 50593792}, {"name": "model.layers.6.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4499021824, "nbytes": 256}, {"name": "model.layers.6.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4499025920, "nbytes": 16777216}, {"name": "model.layers.6.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4515803136, "nbytes": 1048576}, {"name": "model.layers.6.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4516851712, "nbytes": 524288}, {"name": "model.layers.6.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4517376000, "nbytes": 65536}, {"name": "model.layers.6.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4517441536, "nbytes": 4096}, {"name": "model.layers.6.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4517445632, "nbytes": 1048576}, {"name": "model.layers.6.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4518494208, "nbytes": 131072}, {"name": "model.layers.6.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4518625280, "nbytes": 2048}, {"name": "model.layers.6.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4518629376, "nbytes": 4096}, {"name": "model.layers.6.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4518633472, "nbytes": 4096}, {"name": "model.layers.7.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4518637568, "nbytes": 4096}, {"name": "model.layers.7.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4518641664, "nbytes": 1048576}, {"name": "model.layers.7.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4519690240, "nbytes": 524288}, {"name": "model.layers.7.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4520214528, "nbytes": 65536}, {"name": "model.layers.7.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4520280064, "nbytes": 4096}, {"name": "model.layers.7.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4520284160, "nbytes": 1048576}, {"name": "model.layers.7.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4521332736, "nbytes": 131072}, {"name": "model.layers.7.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4521463808, "nbytes": 2048}, {"name": "model.layers.7.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4521467904, "nbytes": 4096}, {"name": "model.layers.7.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4521472000, "nbytes": 4096}, {"name": "model.layers.7.self_attn.k_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 4521476096, "nbytes": 512}, {"name": "model.layers.7.self_attn.o_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4521480192, "nbytes": 16777216}, {"name": "model.layers.7.self_attn.q_norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256], "global_off": 4538257408, "nbytes": 512}, {"name": "model.layers.7.self_attn.qkv_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [9216, 2048], "global_off": 4538261504, "nbytes": 37748736}, {"name": "model.layers.8.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4576010240, "nbytes": 4096}, {"name": "model.layers.8.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4576014336, "nbytes": 64}, {"name": "model.layers.8.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4576018432, "nbytes": 65536}, {"name": "model.layers.8.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4576083968, "nbytes": 64}, {"name": "model.layers.8.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4576088064, "nbytes": 50593792}, {"name": "model.layers.8.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4626681856, "nbytes": 256}, {"name": "model.layers.8.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4626685952, "nbytes": 16777216}, {"name": "model.layers.8.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4643463168, "nbytes": 1048576}, {"name": "model.layers.8.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4644511744, "nbytes": 524288}, {"name": "model.layers.8.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4645036032, "nbytes": 65536}, {"name": "model.layers.8.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4645101568, "nbytes": 4096}, {"name": "model.layers.8.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4645105664, "nbytes": 1048576}, {"name": "model.layers.8.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4646154240, "nbytes": 131072}, {"name": "model.layers.8.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4646285312, "nbytes": 2048}, {"name": "model.layers.8.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4646289408, "nbytes": 4096}, {"name": "model.layers.8.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4646293504, "nbytes": 4096}, {"name": "model.layers.9.input_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4646297600, "nbytes": 4096}, {"name": "model.layers.9.linear_attn.A_log", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4646301696, "nbytes": 64}, {"name": "model.layers.9.linear_attn.conv1d.weight", "kind": "weight", "dtype": "bfloat16", "shape": [8192, 1, 4], "global_off": 4646305792, "nbytes": 65536}, {"name": "model.layers.9.linear_attn.dt_bias", "kind": "weight", "dtype": "bfloat16", "shape": [32], "global_off": 4646371328, "nbytes": 64}, {"name": "model.layers.9.linear_attn.in_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [12352, 2048], "global_off": 4646375424, "nbytes": 50593792}, {"name": "model.layers.9.linear_attn.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [128], "global_off": 4696969216, "nbytes": 256}, {"name": "model.layers.9.linear_attn.out_proj.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048, 4096], "global_off": 4696973312, "nbytes": 16777216}, {"name": "model.layers.9.mlp.gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [256, 2048], "global_off": 4713750528, "nbytes": 1048576}, {"name": "model.layers.9.mlp.shared_expert.down_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [2048, 256], "global_off": 4714799104, "nbytes": 524288}, {"name": "model.layers.9.mlp.shared_expert.down_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [2048, 32], "global_off": 4715323392, "nbytes": 65536}, {"name": "model.layers.9.mlp.shared_expert.down_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [2048], "global_off": 4715388928, "nbytes": 4096}, {"name": "model.layers.9.mlp.shared_expert.gate_up_proj.weight", "kind": "weight", "dtype": "uint8", "shape": [1024, 1024], "global_off": 4715393024, "nbytes": 1048576}, {"name": "model.layers.9.mlp.shared_expert.gate_up_proj.weight_scale", "kind": "weight", "dtype": "float8_e4m3fn", "shape": [1024, 128], "global_off": 4716441600, "nbytes": 131072}, {"name": "model.layers.9.mlp.shared_expert.gate_up_proj.weight_global", "kind": "weight", "dtype": "float16", "shape": [1024], "global_off": 4716572672, "nbytes": 2048}, {"name": "model.layers.9.mlp.shared_expert_gate.weight", "kind": "weight", "dtype": "bfloat16", "shape": [1, 2048], "global_off": 4716576768, "nbytes": 4096}, {"name": "model.layers.9.post_attention_layernorm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4716580864, "nbytes": 4096}, {"name": "model.norm.weight", "kind": "weight", "dtype": "bfloat16", "shape": [2048], "global_off": 4716584960, "nbytes": 4096}, {"name": "gate_up_packed#L00000", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 4716589056, "nbytes": 268435456}, {"name": "gate_up_scale#L00000", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 4985024512, "nbytes": 33554432}, {"name": "gate_up_global#L00000", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 5018578944, "nbytes": 524288}, {"name": "down_packed#L00000", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 5019103232, "nbytes": 134217728}, {"name": "down_scale#L00000", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 5153320960, "nbytes": 16777216}, {"name": "down_global#L00000", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 5170098176, "nbytes": 1048576}, {"name": "gate_up_packed#L00001", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 5171146752, "nbytes": 268435456}, {"name": "gate_up_scale#L00001", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 5439582208, "nbytes": 33554432}, {"name": "gate_up_global#L00001", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 5473136640, "nbytes": 524288}, {"name": "down_packed#L00001", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 5473660928, "nbytes": 134217728}, {"name": "down_scale#L00001", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 5607878656, "nbytes": 16777216}, {"name": "down_global#L00001", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 5624655872, "nbytes": 1048576}, {"name": "gate_up_packed#L00002", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 5625704448, "nbytes": 268435456}, {"name": "gate_up_scale#L00002", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 5894139904, "nbytes": 33554432}, {"name": "gate_up_global#L00002", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 5927694336, "nbytes": 524288}, {"name": "down_packed#L00002", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 5928218624, "nbytes": 134217728}, {"name": "down_scale#L00002", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 6062436352, "nbytes": 16777216}, {"name": "down_global#L00002", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 6079213568, "nbytes": 1048576}, {"name": "gate_up_packed#L00003", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 6080262144, "nbytes": 268435456}, {"name": "gate_up_scale#L00003", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 6348697600, "nbytes": 33554432}, {"name": "gate_up_global#L00003", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 6382252032, "nbytes": 524288}, {"name": "down_packed#L00003", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 6382776320, "nbytes": 134217728}, {"name": "down_scale#L00003", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 6516994048, "nbytes": 16777216}, {"name": "down_global#L00003", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 6533771264, "nbytes": 1048576}, {"name": "gate_up_packed#L00004", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 6534819840, "nbytes": 268435456}, {"name": "gate_up_scale#L00004", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 6803255296, "nbytes": 33554432}, {"name": "gate_up_global#L00004", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 6836809728, "nbytes": 524288}, {"name": "down_packed#L00004", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 6837334016, "nbytes": 134217728}, {"name": "down_scale#L00004", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 6971551744, "nbytes": 16777216}, {"name": "down_global#L00004", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 6988328960, "nbytes": 1048576}, {"name": "gate_up_packed#L00005", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 6989377536, "nbytes": 268435456}, {"name": "gate_up_scale#L00005", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 7257812992, "nbytes": 33554432}, {"name": "gate_up_global#L00005", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 7291367424, "nbytes": 524288}, {"name": "down_packed#L00005", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 7291891712, "nbytes": 134217728}, {"name": "down_scale#L00005", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 7426109440, "nbytes": 16777216}, {"name": "down_global#L00005", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 7442886656, "nbytes": 1048576}, {"name": "gate_up_packed#L00006", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 7443935232, "nbytes": 268435456}, {"name": "gate_up_scale#L00006", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 7712370688, "nbytes": 33554432}, {"name": "gate_up_global#L00006", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 7745925120, "nbytes": 524288}, {"name": "down_packed#L00006", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 7746449408, "nbytes": 134217728}, {"name": "down_scale#L00006", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 7880667136, "nbytes": 16777216}, {"name": "down_global#L00006", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 7897444352, "nbytes": 1048576}, {"name": "gate_up_packed#L00007", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 7898492928, "nbytes": 268435456}, {"name": "gate_up_scale#L00007", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 8166928384, "nbytes": 33554432}, {"name": "gate_up_global#L00007", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 8200482816, "nbytes": 524288}, {"name": "down_packed#L00007", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 8201007104, "nbytes": 134217728}, {"name": "down_scale#L00007", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 8335224832, "nbytes": 16777216}, {"name": "down_global#L00007", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 8352002048, "nbytes": 1048576}, {"name": "gate_up_packed#L00008", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 8353050624, "nbytes": 268435456}, {"name": "gate_up_scale#L00008", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 8621486080, "nbytes": 33554432}, {"name": "gate_up_global#L00008", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 8655040512, "nbytes": 524288}, {"name": "down_packed#L00008", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 8655564800, "nbytes": 134217728}, {"name": "down_scale#L00008", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 8789782528, "nbytes": 16777216}, {"name": "down_global#L00008", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 8806559744, "nbytes": 1048576}, {"name": "gate_up_packed#L00010", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 8807608320, "nbytes": 268435456}, {"name": "gate_up_scale#L00010", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 9076043776, "nbytes": 33554432}, {"name": "gate_up_global#L00010", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 9109598208, "nbytes": 524288}, {"name": "down_packed#L00010", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 9110122496, "nbytes": 134217728}, {"name": "down_scale#L00010", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 9244340224, "nbytes": 16777216}, {"name": "down_global#L00010", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 9261117440, "nbytes": 1048576}, {"name": "gate_up_packed#L00011", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 9262166016, "nbytes": 268435456}, {"name": "gate_up_scale#L00011", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 9530601472, "nbytes": 33554432}, {"name": "gate_up_global#L00011", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 9564155904, "nbytes": 524288}, {"name": "down_packed#L00011", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 9564680192, "nbytes": 134217728}, {"name": "down_scale#L00011", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 9698897920, "nbytes": 16777216}, {"name": "down_global#L00011", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 9715675136, "nbytes": 1048576}, {"name": "gate_up_packed#L00009", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 9716723712, "nbytes": 268435456}, {"name": "gate_up_scale#L00009", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 9985159168, "nbytes": 33554432}, {"name": "gate_up_global#L00009", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 10018713600, "nbytes": 524288}, {"name": "down_packed#L00009", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 10019237888, "nbytes": 134217728}, {"name": "down_scale#L00009", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 10153455616, "nbytes": 16777216}, {"name": "down_global#L00009", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 10170232832, "nbytes": 1048576}, {"name": "gate_up_packed#L00012", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 10171281408, "nbytes": 268435456}, {"name": "gate_up_scale#L00012", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 10439716864, "nbytes": 33554432}, {"name": "gate_up_global#L00012", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 10473271296, "nbytes": 524288}, {"name": "down_packed#L00012", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 10473795584, "nbytes": 134217728}, {"name": "down_scale#L00012", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 10608013312, "nbytes": 16777216}, {"name": "down_global#L00012", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 10624790528, "nbytes": 1048576}, {"name": "gate_up_packed#L00013", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 10625839104, "nbytes": 268435456}, {"name": "gate_up_scale#L00013", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 10894274560, "nbytes": 33554432}, {"name": "gate_up_global#L00013", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 10927828992, "nbytes": 524288}, {"name": "down_packed#L00013", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 10928353280, "nbytes": 134217728}, {"name": "down_scale#L00013", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 11062571008, "nbytes": 16777216}, {"name": "down_global#L00013", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 11079348224, "nbytes": 1048576}, {"name": "gate_up_packed#L00014", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 11080396800, "nbytes": 268435456}, {"name": "gate_up_scale#L00014", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 11348832256, "nbytes": 33554432}, {"name": "gate_up_global#L00014", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 11382386688, "nbytes": 524288}, {"name": "down_packed#L00014", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 11382910976, "nbytes": 134217728}, {"name": "down_scale#L00014", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 11517128704, "nbytes": 16777216}, {"name": "down_global#L00014", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 11533905920, "nbytes": 1048576}, {"name": "gate_up_packed#L00015", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 11534954496, "nbytes": 268435456}, {"name": "gate_up_scale#L00015", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 11803389952, "nbytes": 33554432}, {"name": "gate_up_global#L00015", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 11836944384, "nbytes": 524288}, {"name": "down_packed#L00015", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 11837468672, "nbytes": 134217728}, {"name": "down_scale#L00015", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 11971686400, "nbytes": 16777216}, {"name": "down_global#L00015", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 11988463616, "nbytes": 1048576}, {"name": "gate_up_packed#L00016", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 11989512192, "nbytes": 268435456}, {"name": "gate_up_scale#L00016", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 12257947648, "nbytes": 33554432}, {"name": "gate_up_global#L00016", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 12291502080, "nbytes": 524288}, {"name": "down_packed#L00016", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 12292026368, "nbytes": 134217728}, {"name": "down_scale#L00016", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 12426244096, "nbytes": 16777216}, {"name": "down_global#L00016", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 12443021312, "nbytes": 1048576}, {"name": "gate_up_packed#L00017", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 12444069888, "nbytes": 268435456}, {"name": "gate_up_scale#L00017", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 12712505344, "nbytes": 33554432}, {"name": "gate_up_global#L00017", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 12746059776, "nbytes": 524288}, {"name": "down_packed#L00017", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 12746584064, "nbytes": 134217728}, {"name": "down_scale#L00017", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 12880801792, "nbytes": 16777216}, {"name": "down_global#L00017", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 12897579008, "nbytes": 1048576}, {"name": "gate_up_packed#L00018", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 12898627584, "nbytes": 268435456}, {"name": "gate_up_scale#L00018", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 13167063040, "nbytes": 33554432}, {"name": "gate_up_global#L00018", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 13200617472, "nbytes": 524288}, {"name": "down_packed#L00018", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 13201141760, "nbytes": 134217728}, {"name": "down_scale#L00018", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 13335359488, "nbytes": 16777216}, {"name": "down_global#L00018", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 13352136704, "nbytes": 1048576}, {"name": "gate_up_packed#L00019", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 13353185280, "nbytes": 268435456}, {"name": "gate_up_scale#L00019", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 13621620736, "nbytes": 33554432}, {"name": "gate_up_global#L00019", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 13655175168, "nbytes": 524288}, {"name": "down_packed#L00019", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 13655699456, "nbytes": 134217728}, {"name": "down_scale#L00019", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 13789917184, "nbytes": 16777216}, {"name": "down_global#L00019", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 13806694400, "nbytes": 1048576}, {"name": "gate_up_packed#L00020", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 13807742976, "nbytes": 268435456}, {"name": "gate_up_scale#L00020", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 14076178432, "nbytes": 33554432}, {"name": "gate_up_global#L00020", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 14109732864, "nbytes": 524288}, {"name": "down_packed#L00020", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 14110257152, "nbytes": 134217728}, {"name": "down_scale#L00020", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 14244474880, "nbytes": 16777216}, {"name": "down_global#L00020", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 14261252096, "nbytes": 1048576}, {"name": "gate_up_packed#L00021", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 14262300672, "nbytes": 268435456}, {"name": "gate_up_scale#L00021", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 14530736128, "nbytes": 33554432}, {"name": "gate_up_global#L00021", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 14564290560, "nbytes": 524288}, {"name": "down_packed#L00021", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 14564814848, "nbytes": 134217728}, {"name": "down_scale#L00021", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 14699032576, "nbytes": 16777216}, {"name": "down_global#L00021", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 14715809792, "nbytes": 1048576}, {"name": "gate_up_packed#L00022", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 14716858368, "nbytes": 268435456}, {"name": "gate_up_scale#L00022", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 14985293824, "nbytes": 33554432}, {"name": "gate_up_global#L00022", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 15018848256, "nbytes": 524288}, {"name": "down_packed#L00022", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 15019372544, "nbytes": 134217728}, {"name": "down_scale#L00022", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 15153590272, "nbytes": 16777216}, {"name": "down_global#L00022", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 15170367488, "nbytes": 1048576}, {"name": "gate_up_packed#L00023", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 15171416064, "nbytes": 268435456}, {"name": "gate_up_scale#L00023", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 15439851520, "nbytes": 33554432}, {"name": "gate_up_global#L00023", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 15473405952, "nbytes": 524288}, {"name": "down_packed#L00023", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 15473930240, "nbytes": 134217728}, {"name": "down_scale#L00023", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 15608147968, "nbytes": 16777216}, {"name": "down_global#L00023", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 15624925184, "nbytes": 1048576}, {"name": "gate_up_packed#L00024", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 15625973760, "nbytes": 268435456}, {"name": "gate_up_scale#L00024", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 15894409216, "nbytes": 33554432}, {"name": "gate_up_global#L00024", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 15927963648, "nbytes": 524288}, {"name": "down_packed#L00024", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 15928487936, "nbytes": 134217728}, {"name": "down_scale#L00024", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 16062705664, "nbytes": 16777216}, {"name": "down_global#L00024", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 16079482880, "nbytes": 1048576}, {"name": "gate_up_packed#L00025", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 16080531456, "nbytes": 268435456}, {"name": "gate_up_scale#L00025", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 16348966912, "nbytes": 33554432}, {"name": "gate_up_global#L00025", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 16382521344, "nbytes": 524288}, {"name": "down_packed#L00025", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 16383045632, "nbytes": 134217728}, {"name": "down_scale#L00025", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 16517263360, "nbytes": 16777216}, {"name": "down_global#L00025", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 16534040576, "nbytes": 1048576}, {"name": "gate_up_packed#L00026", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 16535089152, "nbytes": 268435456}, {"name": "gate_up_scale#L00026", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 16803524608, "nbytes": 33554432}, {"name": "gate_up_global#L00026", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 16837079040, "nbytes": 524288}, {"name": "down_packed#L00026", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 16837603328, "nbytes": 134217728}, {"name": "down_scale#L00026", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 16971821056, "nbytes": 16777216}, {"name": "down_global#L00026", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 16988598272, "nbytes": 1048576}, {"name": "gate_up_packed#L00027", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 16989646848, "nbytes": 268435456}, {"name": "gate_up_scale#L00027", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 17258082304, "nbytes": 33554432}, {"name": "gate_up_global#L00027", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 17291636736, "nbytes": 524288}, {"name": "down_packed#L00027", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 17292161024, "nbytes": 134217728}, {"name": "down_scale#L00027", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 17426378752, "nbytes": 16777216}, {"name": "down_global#L00027", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 17443155968, "nbytes": 1048576}, {"name": "gate_up_packed#L00028", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 17444204544, "nbytes": 268435456}, {"name": "gate_up_scale#L00028", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 17712640000, "nbytes": 33554432}, {"name": "gate_up_global#L00028", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 17746194432, "nbytes": 524288}, {"name": "down_packed#L00028", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 17746718720, "nbytes": 134217728}, {"name": "down_scale#L00028", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 17880936448, "nbytes": 16777216}, {"name": "down_global#L00028", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 17897713664, "nbytes": 1048576}, {"name": "gate_up_packed#L00029", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 17898762240, "nbytes": 268435456}, {"name": "gate_up_scale#L00029", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 18167197696, "nbytes": 33554432}, {"name": "gate_up_global#L00029", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 18200752128, "nbytes": 524288}, {"name": "down_packed#L00029", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 18201276416, "nbytes": 134217728}, {"name": "down_scale#L00029", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 18335494144, "nbytes": 16777216}, {"name": "down_global#L00029", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 18352271360, "nbytes": 1048576}, {"name": "gate_up_packed#L00030", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 18353319936, "nbytes": 268435456}, {"name": "gate_up_scale#L00030", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 18621755392, "nbytes": 33554432}, {"name": "gate_up_global#L00030", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 18655309824, "nbytes": 524288}, {"name": "down_packed#L00030", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 18655834112, "nbytes": 134217728}, {"name": "down_scale#L00030", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 18790051840, "nbytes": 16777216}, {"name": "down_global#L00030", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 18806829056, "nbytes": 1048576}, {"name": "gate_up_packed#L00031", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 18807877632, "nbytes": 268435456}, {"name": "gate_up_scale#L00031", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 19076313088, "nbytes": 33554432}, {"name": "gate_up_global#L00031", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 19109867520, "nbytes": 524288}, {"name": "down_packed#L00031", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 19110391808, "nbytes": 134217728}, {"name": "down_scale#L00031", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 19244609536, "nbytes": 16777216}, {"name": "down_global#L00031", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 19261386752, "nbytes": 1048576}, {"name": "gate_up_packed#L00032", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 19262435328, "nbytes": 268435456}, {"name": "gate_up_scale#L00032", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 19530870784, "nbytes": 33554432}, {"name": "gate_up_global#L00032", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 19564425216, "nbytes": 524288}, {"name": "down_packed#L00032", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 19564949504, "nbytes": 134217728}, {"name": "down_scale#L00032", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 19699167232, "nbytes": 16777216}, {"name": "down_global#L00032", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 19715944448, "nbytes": 1048576}, {"name": "gate_up_packed#L00033", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 19716993024, "nbytes": 268435456}, {"name": "gate_up_scale#L00033", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 19985428480, "nbytes": 33554432}, {"name": "gate_up_global#L00033", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 20018982912, "nbytes": 524288}, {"name": "down_packed#L00033", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 20019507200, "nbytes": 134217728}, {"name": "down_scale#L00033", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 20153724928, "nbytes": 16777216}, {"name": "down_global#L00033", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 20170502144, "nbytes": 1048576}, {"name": "gate_up_packed#L00034", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 20171550720, "nbytes": 268435456}, {"name": "gate_up_scale#L00034", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 20439986176, "nbytes": 33554432}, {"name": "gate_up_global#L00034", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 20473540608, "nbytes": 524288}, {"name": "down_packed#L00034", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 20474064896, "nbytes": 134217728}, {"name": "down_scale#L00034", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 20608282624, "nbytes": 16777216}, {"name": "down_global#L00034", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 20625059840, "nbytes": 1048576}, {"name": "gate_up_packed#L00035", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 20626108416, "nbytes": 268435456}, {"name": "gate_up_scale#L00035", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 20894543872, "nbytes": 33554432}, {"name": "gate_up_global#L00035", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 20928098304, "nbytes": 524288}, {"name": "down_packed#L00035", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 20928622592, "nbytes": 134217728}, {"name": "down_scale#L00035", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 21062840320, "nbytes": 16777216}, {"name": "down_global#L00035", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 21079617536, "nbytes": 1048576}, {"name": "gate_up_packed#L00036", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 21080666112, "nbytes": 268435456}, {"name": "gate_up_scale#L00036", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 21349101568, "nbytes": 33554432}, {"name": "gate_up_global#L00036", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 21382656000, "nbytes": 524288}, {"name": "down_packed#L00036", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 21383180288, "nbytes": 134217728}, {"name": "down_scale#L00036", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 21517398016, "nbytes": 16777216}, {"name": "down_global#L00036", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 21534175232, "nbytes": 1048576}, {"name": "gate_up_packed#L00037", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 21535223808, "nbytes": 268435456}, {"name": "gate_up_scale#L00037", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 21803659264, "nbytes": 33554432}, {"name": "gate_up_global#L00037", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 21837213696, "nbytes": 524288}, {"name": "down_packed#L00037", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 21837737984, "nbytes": 134217728}, {"name": "down_scale#L00037", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 21971955712, "nbytes": 16777216}, {"name": "down_global#L00037", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 21988732928, "nbytes": 1048576}, {"name": "gate_up_packed#L00038", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 21989781504, "nbytes": 268435456}, {"name": "gate_up_scale#L00038", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 22258216960, "nbytes": 33554432}, {"name": "gate_up_global#L00038", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 22291771392, "nbytes": 524288}, {"name": "down_packed#L00038", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 22292295680, "nbytes": 134217728}, {"name": "down_scale#L00038", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 22426513408, "nbytes": 16777216}, {"name": "down_global#L00038", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 22443290624, "nbytes": 1048576}, {"name": "gate_up_packed#L00039", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 1024, 1024], "global_off": 22444339200, "nbytes": 268435456}, {"name": "gate_up_scale#L00039", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 1024, 128], "global_off": 22712774656, "nbytes": 33554432}, {"name": "gate_up_global#L00039", "kind": "experts_bank", "dtype": "float16", "shape": [256, 1024], "global_off": 22746329088, "nbytes": 524288}, {"name": "down_packed#L00039", "kind": "experts_bank", "dtype": "uint8", "shape": [256, 2048, 256], "global_off": 22746853376, "nbytes": 134217728}, {"name": "down_scale#L00039", "kind": "experts_bank", "dtype": "float8_e4m3fn", "shape": [256, 2048, 32], "global_off": 22881071104, "nbytes": 16777216}, {"name": "down_global#L00039", "kind": "experts_bank", "dtype": "float16", "shape": [256, 2048], "global_off": 22897848320, "nbytes": 1048576}], "shards": [{"file": "freetoken-00000.ftw", "global_off": 0, "nbytes": 8353050624}, {"file": "freetoken-00001.ftw", "global_off": 8353050624, "nbytes": 8484552704}, {"file": "freetoken-00002.ftw", "global_off": 16837603328, "nbytes": 6061293568}], "source_model_path": "C:\\Users\\Remix\\.freetoken\\models\\KAT-Coder-V2.5-Dev-NVFP4A16", "fingerprint": "bd7d4fc1d723e1b3", "quant_format": "nvfp4", "expert_bank_num_layers": 40, "counts": {"weight": 623, "experts_bank": 240}, "copied_metadata": [".gitattributes", "chat_template.jinja", "config.json", "configuration.json", "generation_config.json", "merges.txt", "preprocessor_config.json", "README.md", "tokenizer.json", "tokenizer_config.json", "video_preprocessor_config.json", "vocab.json"]} |