{ "metadata": { "ParamSize": 325, "ParamBytes": 4517413888.0, "BitsPerParam": 4.500381276979491 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262672384, "records": [ { "name": "lm_head.q_weight", "shape": [ 128258, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262672384, "byteOffset": 0 } ], "md5sum": "70739a6dab069b4bd2b01c03aec45113" }, { "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": "c77580b7652685b6e080d27485094105" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32842240, "records": [ { "name": "lm_head.q_scale", "shape": [ 128258, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32834048, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32834048 } ], "md5sum": "3d06cebaf3de323b0d282f3ec186d923" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 262672384, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128258, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262672384, "byteOffset": 0 } ], "md5sum": "1d13fd2c0576580f17797493037db0ab" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32834048, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128258, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32834048, "byteOffset": 0 } ], "md5sum": "3eefb4cd90b0ae7eb2ffd5e20e680e55" }, { "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": "06381c54ea89e9ddca4b01cbc9cdc592" }, { "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": "f6d24379b02f3136d6a8adfe91628c9f" }, { "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": "712899bf271b536de8feb44d6c9214a0" }, { "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": "9170132bef439efbec6b480612783201" }, { "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": "190e62f90d2a7d804b93d5a808eee916" }, { "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": "44f6449d24844632bf87937e2a7eb3d7" }, { "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": "5ce0a7f97f43d03a88ab957a8d8124b4" }, { "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": "9c504a82302ce61362c7f239128a74b7" }, { "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": "21c98b2d8e55ab16cf951c6235efc56b" }, { "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": "90eb7700efec8c2ea32a26f8c8497a86" }, { "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": "463d8aacc49eec4d46dee292d46012aa" }, { "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": "247e535ac6223797ce7c778cef1ffc5c" }, { "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": "2a3fd2e1eb485b1a24dfb88230374c16" }, { "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": "c9014c057fb722f26ad192205ff43ce4" }, { "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": "009a12152249880ba2bc1f193a975b10" }, { "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": "585918dac86990f27de7f9f301e21d93" }, { "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": "fb8286a5f0d073f1ae898f33f6e05cba" }, { "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": "e7acb1842a124fb40902fbecadb18534" }, { "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": "6b27fe45ce11a64a27d0c000f0743b8c" }, { "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": "617a0c9b89c501edc2e9d2d293ad351d" }, { "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": "d4ef5658ab27f9cd4f796d79c74e2e44" }, { "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": "f03417b90b9c97ebe637c176d2641e4a" }, { "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": "1f77981ea0d7f55082fbf1c6858805ff" }, { "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": "62ae5a5bfb7af0d07d18b858ba75899a" }, { "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": "37b449cc0a6f15fd87ab4234c9009ae0" }, { "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": "e01666b1d40aa6eb2f67c51dde7a9acd" }, { "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": "1943be1148292a108ac078be93134b6b" }, { "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": "bb5ef7f78b404ab7e72ae9b42d8238b8" }, { "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": "d11ae168abf62cb0478f08317e78e4d5" }, { "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": "83f9ae8a1fac76a5405337755ca4f339" }, { "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": "96be712e034493cb58b0cdeb3ceab62e" }, { "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": "dceff03b159b7b2de9afc42c45c4c2c8" }, { "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": "5425bd5e904244531348a587637856f4" }, { "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": "b1f0da42d56e926808f78eb0a7d0e900" }, { "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": "0af37a5725e0d5110e3b33731d998ac7" }, { "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": "e12ddcc1ac9c3f4783abbe47c319e81c" }, { "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": "94314b3e1440bd8725395347398eebb1" }, { "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": "8364b38859bf151f6d538bcc4ddfc433" }, { "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": "c7ef9f92f593bedc5331d72dc6017ac9" }, { "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": "805f5d9b3f12d97c5afbbec5ee3c9e4d" }, { "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": "e600fbb88cc7de7fe93f66cfc3192c19" }, { "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": "8a4b50bc3ed5fd45bd00858ba1db1e01" }, { "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": "ee180f5cb75c6d7b67fa13e85f578db1" }, { "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": "91ac8a06038e7e82cb8ae64a2fbf02fa" }, { "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": "3412f2c33fc8ed5566635ef4e1c63494" }, { "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": "cc8a3f3d7ebf78fc5be43776c28e550b" }, { "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": "b333e9c9e64eaf4e722fdef628b981c4" }, { "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": "c853910f792191c12cb48b8a37b3b2a7" }, { "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": "a7cbc0e58fea6a28aa4e4aeac995cdfe" }, { "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": "f88c66eb3deab37b7448a6441a1d1307" }, { "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": "e8adb38f5a7ececa3f9d824b580524c8" }, { "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": "6c14054769a73194b3cfd128afb9a606" }, { "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": "301a70a7ceba2dbbb096364be29c4589" }, { "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": "0f555c40bd70bc735389e2d8d71927a8" }, { "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": "3666a8d8dd20b31ada0e1bac69084813" }, { "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": "c60c6e3b78e19c533cb21104a772be8f" }, { "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": "43e6d5e732b6c5b17ab1acc1b2582187" }, { "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": "5f62370363733f4ff5d84a71e42846e5" }, { "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": "25129ba5ce5bcf54483913b7cd9ebba5" }, { "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": "7293990024485e6732e1e9dd28932a03" }, { "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": "73ecec54304bccb77b20a14989e51c28" }, { "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": "390917c2735c477826c20c7b334634ed" }, { "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": "7abcfa9a34be727ee8e86ec79c48c27b" }, { "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": "5745483d21d2351c84ff9b125f59505d" }, { "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": "213e2828c5232c555cc7ecc93aaae8a1" }, { "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": "ad859ae5975c9b52ec8d646aedbefddf" }, { "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": "29272d11c3c50ad15abb236fe2aa8e25" }, { "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": "3dd7348f3064e965c4bcd18935ac6b31" }, { "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": "dfe9554e05b3f874b29a8558e96489df" }, { "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": "bccda4f755366897a255b0bdd9754e74" }, { "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": "35078a5bfe47354813c7a088a973171e" }, { "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": "6050f6698d3fc0e1486e8f444f7a1483" }, { "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": "3983f93168e9a40bdc988c8351482cfc" }, { "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": "6680a304bc7afd32b3e531b952a84d7f" }, { "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": "e2f553572a3bfd1bd45019bfd675b21d" }, { "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": "bd5b79659ff0fbd377da43f824466c09" }, { "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": "96ac87d384a43fd74c0b6779c9324138" }, { "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": "710cd9668230240f3d1282786af77381" }, { "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": "6bae7de2c3ea2b6677cd7b993ffc5f4e" }, { "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": "eee2efec9b56c268c2880fdcb595d361" }, { "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": "3977fb31a483e37217bbcecfd5e280c2" }, { "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": "6e994a325ec8d0e6adc52fef1a67dfb1" }, { "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": "6977d41a12ff8441d2eae066b54a13cd" }, { "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": "395289dc7486f9c7df9deea39922acbb" }, { "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": "a485ab7dc3567b09f7758efe5156f15b" }, { "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": "c9cfcc6584d629038595d2e7548b5523" }, { "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": "cb0b353468de007140435b15fd58ead8" }, { "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": "18f4dde65fe81ff0853adc910b6f190a" }, { "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": "bd6ef552fab3e709b9a4f535f8287941" }, { "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": "34faa2513f500ff7e9adeca9027ecb86" }, { "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": "7328cabdc0d669cf6f68ca916814fead" }, { "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": "92ef1ef91ff1b4adcc2de5417ff5fabd" }, { "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": "51f0ee7f8d05f07a4d5c5beb7414aa03" }, { "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": "f7f9da7d12cabab129066e30edf39adb" }, { "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": "2727c6f42082cc7bae0939940f1efa27" }, { "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": "0756962265e181767f2fe964282806bb" }, { "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": "aba597d25073132651f3263bfa4b4d10" }, { "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": "fb0c18d2c6f0728183becc987de1e10a" }, { "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": "e9769c6b44308408b3645a74efcaeee2" }, { "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": "4ebe7f898dce9d1152fea93d8ce8714f" }, { "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": "534a0aa932cbcf5f3a2f77cc8e80e95f" }, { "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": "700eb7210421ad6ed66e2f6871960bdd" }, { "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": "c0faa99a7bb4e44c5bc31a73814af3b9" } ] }