{ "metadata": { "ParamSize": 183, "ParamBytes": 1409830912.0, "BitsPerParam": 4.500347711112945 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262144000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 256000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262144000, "byteOffset": 0 } ], "md5sum": "4500be88779baf43abfc8597bf8cf1fe" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "a05be97c93213549dce4e5cecb2df671" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32772096, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 256000, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32768000 } ], "md5sum": "f379b208c95b8217c994896c7b6f2498" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6c2e831a732c42208aeea2eca1d1e7da" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c08c393db5f172af2d91de03d139a8cd" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 30482432, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 2097152 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 6291456 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 6295552 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 8916992 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9244672 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 11341824 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11603968 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28385280 } ], "md5sum": "0e660c3a18a7718f50de01d1a96bf3c7" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "132b02e713d04b72ed9e1bab84710017" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "62e161266d03e108e4bc8dda8cff9315" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fa941839a74a08f8684196f3fc4c7dde" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "e518d309cfbdb5f4e6602c5d69ed7d48" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f9a78497c40303645cc2f687aafd4140" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "a94e8087b62f4b859fb02b3238202d7c" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "db1bd48e7e1bb87a18a2b880ba8f5cc3" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "ce1f0f6aa9b0cc43225d96ba93fce3eb" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c3315c13bf547d6f26c24ff9cf129f03" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "81e987290592424c3c0781848dbb9b0b" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2f704ab2d7b68654159cc3e0e4e939d6" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "c5102c6a2799c7ddd96ed8e1fcae05a0" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fc125415a193b35284f6ad987e48b91c" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0d740a66159f30a2a2d511a3b81df042" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 32841728, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28647424 } ], "md5sum": "dee9fd244834cb17e1ba2e4f926fd4a9" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2e23bdf9c20b784406ed77be4d89ec48" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "d5eb43d5b392f0c695c729438d4d612f" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2441e9f38d5c3124886510e1111504e4" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "07752128a818a38a32ebe472b009c170" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d2202bda44526904918c703172f6ee5a" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "7a42f08fd6179044fbed94c53255d87f" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dc573f47986a837861c129e25f62f0f2" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "8a39116d6e92db1b65aac2995df86407" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8af97b02756aff69a1c3a4866f490876" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "439da4b9f963c3c671d13f9572156b49" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "25b815c65b469bec26b1fc64edd55ac7" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "6125a2f468bd6cdea4bb324410561bf7" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9f90fd3ddceb9d5f382cf5b63328b07d" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "b9183414a88c1e809ebc8f2a0565a614" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "727d67cdc4771e3245b726422b1847d7" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "bbe60bb86e8a7f6eecda6f85dce4d74e" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 24195072, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24186880 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24190976 } ], "md5sum": "eaa64e8ef7f6231167a3229622b31042" } ] }