{ "metadata": { "ParamSize": 325, "ParamBytes": 4517404672.0, "BitsPerParam": 4.500381277757404 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262668288, "records": [ { "name": "lm_head.q_weight", "shape": [ 128256, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262668288, "byteOffset": 0 } ], "md5sum": "96d80a43175f832669b92448d48d7854" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "064e3ae33ba29834f1ce9333ae46a2c5" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32841728, "records": [ { "name": "lm_head.q_scale", "shape": [ 128256, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32833536, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32833536 } ], "md5sum": "b273fa59cdfdd1f4d5487378775cb170" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 262668288, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262668288, "byteOffset": 0 } ], "md5sum": "377e5b6ed8b2ad8049461e0a4aa34752" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32833536, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32833536, "byteOffset": 0 } ], "md5sum": "ec1f5c954a5962ff7a038ec0f8e110e2" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 33054720, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3670016 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3678208 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3686400 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 3694592 } ], "md5sum": "556bc706d952da3438664b558cadf61e" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "c97e4d84ca97b9a9314d0fed806a963d" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "f143108d76aeb51bef6e85c10a82f173" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "75e98b1c70e3696fc68ae4fc97017209" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5bd1e6ff3d1196db52fd9bcbe0e69808" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "5c69450d9e2c8dd627e93b5693b086e4" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "02987ba38bc688176d9ffcc886dd5383" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "3ad964d2904cb310ae4f83b18832966e" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "955c12c51d61ca3be7f9bb150f8caea0" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f8142821e741fb2dbe892ebc8a96c328" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e7af41163b13fcb6112f6e7a5fa54021" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "dc6c6a46d13d7681f05b5e0964db3814" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3a030ad5ee1a1bcff744c02d1688f33c" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "4091e52e38fc2d281e081a7a21bfde56" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "85d1dfc9ca77e2539895f9e2909e6a8a" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "34941f076b82b5b9f2c9b49888cfed66" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "58e3ef0444e8d5e7186d6c13a92f51d7" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "8122c483644d542c22467603f52e8340" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "83d0975bdb0c424e43d3c67760480ac9" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "39d578123674b9d9bbe45007e8645a40" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5ca8c78b9142989f0d2da5a49b044acb" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "536db68244d1a1f61749fa2bc46b5aee" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b0a62df906a787a8fbcd19f9a2f05b5b" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d1142b5b2ab648e8e484a3b2a8006512" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "a104f85d6c724ffabd90efdc59ed72f0" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a27813ca5ff5c5dd2057ae07ea32e556" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "4916363bbb205989ef9bfbf4a735c147" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9ac153cf4403f970481d96f3afa9c63c" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "1ba49421972e1f1e45935d002c3dc7ba" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3a3922114017e0fe323a2d20c9b8d89e" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f69b547b7246d359f471bba6ca7ad4da" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "7528e9241c37248a947c1124bd383fc4" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0fbda6bed21d4b5cdf9efca359fc43d1" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "46d9b8f168088c02fbe2916289f0a811" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "f0858d91dfcf569aee067059b0ed17fd" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9d64f4fac24ef9fd41b17957258a4991" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "db520b821e8ebaabe05d53c9f2e74e68" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "d37a0bc301aecb4acb55e9e59bf43ffc" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9c8944db9360660ac5bcd66772b9e8d5" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "45df8290d44f47260e83ec19af95be10" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "419abdd7b1525f166b1604c44dc08f1c" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "8807ade59a55d477ed49652b35b89da5" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "df1b48612ac5fd0bd389d666782e0a3b" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ff9ef3722cdc2e0be48de42f954e78c4" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "1ec654047960b98fe7173832a15af280" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "131ba3ed2a33e3884a6d8766f58b41f8" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "d707afddb59c9078063acbeb9480dcab" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "1a37c79ee7c991f3dae37312ca178ec7" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c5986793bb7a7f55a88794a902c5308e" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "21107dd92936beb1de03249b3aaca22c" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "73c2736e61075dfca9a4f9292022586e" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "69a1c407874447c056cdf1610ee0b1d9" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "c5311fa7fcef78eefafad3951cb250fb" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "cfd86b3bb0a9a46eff97a355830a4751" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "605863e9070761dd191716d0bc07e358" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "37a98cce6ecd80d676170150a1a05cc9" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ed7030a6ea301aa5d7087cae6ae363cf" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "5e597b2159671df6f165b909a8c51da8" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ab955f25d06a530eeb37a746563ae40c" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "70d907600766b038f6d41774d9ce68bb" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "47ff27884e829e28609762d28a2282ae" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9a09fb5c42ad64dfb0173a03d6a68f11" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 30932992, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 23592960 } ], "md5sum": "0e506882fc4608713a7096cf78e2efe5" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "58f243a6a6ca5b74d69a8ac4e73bbfb0" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "a4f67c429de28647feb2ae02f97e3e94" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "50b142976a8c3a58cd77be4f63ba67c0" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "1be91867f187cc8ab2fefd1b35d1e386" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "ecef6b5bf0d5ad9ed199f89f017b8c3a" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3670016 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 3678208 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 3686400 } ], "md5sum": "8d3e507443c042487684d7ebcf0ce8dd" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "1df676d51019940935aa48687861ec41" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "d39acb822ed3b9cf2e918430b4169cd9" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "81724d70d741d2d81ae19a721762ade8" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "5f0c54612fe7a3a6afa5d055b386d6d3" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "b6c15c10fb7fc0dcdbd04fc0cbb0cf46" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "fb660565ba40149d0421d29f4d25e435" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "19e6a4b653e2cd9e8f513a73169380ca" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "719ab8395a427fcea55a124d1c076463" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8bbce5cac5992a373dae9f3f1e432207" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "f50ea2ac55fa34b358283382b24f0cc0" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "cf59049ec9fc4e101d7891dbeea999d9" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "413d17e652fc27f1304d0c783768e95b" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "df274722270666bfb31f5e52956d6471" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "080197912e4d4fa5c08b61ba4925df46" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "13bb5351f0156b2018242cb4be2079e9" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d7032528ebed155ad65b778146b529dd" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9b7f08c786f35993cc005506b96c332d" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "43843d61dd1a8247186e390a6ef6f0a2" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "10fd857cd514997abc6aa0c8f2601122" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "249a052a263de62197fc70778067acfe" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 22036480, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 11018240 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 14688256 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 22028288 } ], "md5sum": "a9561f327066f356e6d58222f0b1878f" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a87a377c9d78372ae5472b50b68b508f" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "ae8a82a1bb9152ba5d1474b82ec5e0a3" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 27271168, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 14155776 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 22544384 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 23592960 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 23601152 } ], "md5sum": "ab2ba510d0e3f674a19b9e373ae8e42a" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a3aa6aff137c77ea5819227a526e0a29" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 30949376, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7340032 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 7348224 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 19931136 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21504000 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29892608 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30941184 } ], "md5sum": "84849fd4815036915186ff8cccefc07f" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "e27c74807f9b9137ce3b381a4c1e5e6f" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 25174016, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 3670016 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11010048 }, { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 11018240 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23601152 } ], "md5sum": "ed465ecf9bf2cf6385b3f0ed07ea2bf5" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "735a7ea03d9190a92bf79d8a7687da3c" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "9324420a7586ac0ccb99430c33bfc841" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33046528, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3670016, "byteOffset": 9445376 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 13115392 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20455424 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 20463616 } ], "md5sum": "3c5336f44e933502c59eeacb79efb6d7" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 58720256, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 58720256, "byteOffset": 0 } ], "md5sum": "bd46f99fd6ec7aa23820b151c10efd4d" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 32505856, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 1572864 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 9961472 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7340032, "byteOffset": 11010048 }, { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 12582912, "byteOffset": 18350080 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 30932992 } ], "md5sum": "bd6a123d9863d2386ea7c1cb0f54ecb7" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 9437184, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 } ], "md5sum": "79dbbc5f198e53f6b2702240f2fee8c7" } ] }