{ "metadata": { "ParamSize": 183, "ParamBytes": 1409830912.0, "BitsPerParam": 4.500347711112945 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262144000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 256000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 262144000, "byteOffset": 0 } ], "md5sum": "4500be88779baf43abfc8597bf8cf1fe" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "cef1b1acce1b13eb751549dad6f495ba" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32772096, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 256000, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32768000 } ], "md5sum": "f379b208c95b8217c994896c7b6f2498" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dfee34f9e0c177f22d49dbac46f8dd5b" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "431e277461fae9c5c613365f5bc3e3d6" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 30482432, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 2097152 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 6291456 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 6295552 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 8916992 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9244672 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 11341824 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11603968 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28385280 } ], "md5sum": "b7701c23974f43e4877f75a68128ec5f" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5e2e497bbdaa9868341443cfd69d30d4" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "e89fc38efd6ff3fcbcae2b798fb139ad" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2a1989727972489cffadefe5ace1bff8" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "43cfd0cb87a86c2da0a7bbfc640fe7aa" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "baba60a2fdd3a996dbad8fdd593100b0" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "2d7d3a4ed5e35fe22497b68068b4151b" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "21ed76d7cdcff3e05d21f9663b698039" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "e039106af34e65cb723ff46f06beb8e5" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ad26eb9489f51155e9e2d61dc9bd7fcf" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "ad76ece934d0f1dfdae5967b580a7279" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "48808099fbaa8ab9d80c9eee5805fe59" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "70c72b4d5fbdef92c4e0794df5bce6d3" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "298d44e755cd36ff0df380f979f22af2" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1484fabc960809a028996ab849710faa" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 32841728, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28647424 } ], "md5sum": "2d2e7a66966b5340be01b664df4480cb" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cba0f7bdaa5a1438d6c019dfac82d016" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "644b75bb5185819fec8e66026e90c66f" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6e925bfe5b753831adcbc4ef79e6ed06" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "9010124ce7608b4ec152dc966606e514" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c582de38d9eea27f41a6c16ae16f468f" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "e563c044b0d227907fd0eba308a805e0" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2c6f2b915c1902ee277db9bb2ceabc7e" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "e16ad28068cb71084513a306f33d2edf" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "069159d0a9dc7ae1d03bd27456551135" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33431552, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24186880 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28381184 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28385280 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31006720 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31334400 } ], "md5sum": "fe6f1b8bf89be3f1d1a284a381253a37" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "be92c3987de454e121a2900a3f30ec11" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "1f5cb663dd770651e60d2133d5212145" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d9e2a7b9629e371b6702f660e0486c39" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 30748672, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 262144 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 266240 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 17043456 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19140608 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23334912 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 23339008 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 25960448 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 28385280 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28647424 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28651520 } ], "md5sum": "441be56b3ba8173f36ea1ccbfd2a4f09" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 32768, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4c887e95e6099c96c8aa49c82dbb1298" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 32583680, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4194304 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4198400 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 6819840 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7147520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 9244672 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 9506816 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9510912 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 26288128 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 32768, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 28385280 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32579584 } ], "md5sum": "1ce594e064600e91f2dc8b6c07ad77e3" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 24195072, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 2621440 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2949120 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 5046272 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 5308416 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 5312512 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 512 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22089728 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24186880 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24190976 } ], "md5sum": "ec3b8f2f60fbfc2833d525eb0b23ba07" } ] }