{ "metadata": { "ParamSize": 163, "ParamBytes": 637317120.0, "BitsPerParam": 4.075508022440898 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131334144, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131334144, "byteOffset": 0 } ], "md5sum": "f648e343a5e154e29bacf95ccd2cf9fe" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 33308672, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4104192, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4104192 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 4108288 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 12496896 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 12759040 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 29536256 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30060544 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 30064640 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 33210368 } ], "md5sum": "a91c3ce23762bb02e632ec4779ef9f75" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33533952, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 2097152 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 2162688 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 2166784 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 10555392 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 10817536 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 27594752 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28119040 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28123136 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 31268864 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 31367168 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 33464320 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33529856 } ], "md5sum": "d784d4dd24e11fd541c33620d6a7f6f0" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "2fdc69b088d835222e951d2160fdbccd" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "aa011975acb711403b527beb39802d23" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "8369453a36c27a90a42c11dc46e31e76" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "a6a7361d64844ec095cedcd9c7bb1056" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "e68f63cf463bd0d25f16a254df105e4d" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "9bfb1ac40978a4b0db65ad1286882ff2" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "8ab5ff76c214c7c0ec7b3d664d3f6069" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "5154d473da34fdaf71d5b5a00e4e2a4c" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "b7a513ea1e71c1a18e48d4ea0453a8b6" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "989731a178c2d8b4377fa09c07998023" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "76445a06209183519822d0d0fb223cc8" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "2a4a7165ca8e3a43ae6ce2b04670bca5" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "9a56c42fa5c9434523511da89466a4f8" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31367168, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 8388608 }, { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 8650752 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 524288, "byteOffset": 25427968 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25952256 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 3072, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 25956352 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 3072, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 98304, "byteOffset": 29102080 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 29200384 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 16 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65536, "byteOffset": 31297536 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31363072 } ], "md5sum": "917c369ac5d877fb20638b067c86fb41" } ] }