{ "metadata": { "ParamSize": 225, "ParamBytes": 687846400.0, "BitsPerParam": 5.002261992750453 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 32770048, "records": [ { "name": "lm_head.q_weight", "shape": [ 32002, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32770048, "byteOffset": 0 } ], "md5sum": "7a1439d14adbc05474a8ea18d1ba9f77" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 32770048, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32002, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32770048, "byteOffset": 0 } ], "md5sum": "93ea74dc1468f8858ea6a3855952d77b" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32977408, "records": [ { "name": "lm_head.q_scale", "shape": [ 32002, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096256, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32002, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096256, "byteOffset": 4096256 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 8192512 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 8196608 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 13963776 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 14684672 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 26219008 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 27660800 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27664896 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 30286336 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30614016 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 32711168 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32973312 } ], "md5sum": "bdc6e1d284dd29fd7e680ae723dbda6d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31268864, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 5767168 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 6488064 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 18022400 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19468288 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22089728 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22417408 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24514560 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 24776704 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 24780800 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 30547968 } ], "md5sum": "f01f3b71c293467d8ed45504eda9226a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "6d81b0738e2126d2f17e4d98a9b0d74d" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "57d0ff39f702fa33beaf06b7ec3a26c3" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "301cf39f724cb4fc42a8d500e6948410" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "1d514b7e7034b1bd068a51957085df21" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "b5b9e2ce708b76c59e8456266f5d2a2a" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "93fd4c1b329fae91f36c84ff6e41b112" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "5065346a2ab51e784b9dda0efb66199f" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "fbec7498f661802858e2bfcad03f1fed" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "e17cdc8eda52b8375706489012083aca" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "193dcfec079b21e12775be4ae32f7a62" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "8627bb6fccc2f2279622024f6134a570" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "191339668c607cafb7da5ef6b5a1a2b6" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "3adf6acb03ae3549278c3368b75556b1" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "d4c8ddf9eb3e82efc0db9c1b95aa0300" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "a921d16fed465ad601fb6e7c61ce2f09" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "0d66a2db698d9ac93ede978c1dcdce7b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "cda0e520c8e05827fc946f91758c9a52" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "825c88f5cee99eeaaf3f56df7136c865" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "f98f9675db63fc507426774f4c258d68" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 18292736, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 } ], "md5sum": "d22d3fe1d4948d71209d80557eaaf819" } ] }