{ "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": "6bf2b42869155ed6a2fd365c1506a677" }, { "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": "c6682a6feaa7374dfd598bde44c25e5e" }, { "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": "b25104c89f2a56af8a09fa40c51b81da" }, { "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": "1f3502cee33933de375ba9c511e3f2d2" }, { "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": "e518fe304ed046b6875a4aa9ed796564" }, { "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": "396fd1e4523e4ad5e309925967d9ad29" }, { "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": "22107eecf614cf70f0c8ec6f8ac521b9" }, { "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": "591f52c166d47a1205142924bd2f9a7b" }, { "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": "ab58efb91f267ddb2dc187525550cf0c" }, { "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": "85ab1d3335f41eab72939bf9aab4a5fe" }, { "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": "85cd6134b5eb0b8971f84834f942bdae" }, { "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": "c128992194b20dfc9200dbddf6ccb660" }, { "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": "ea351a31f2c12837f37739a48a24bf4f" }, { "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": "e7b5f2045b1c916d29c7ba8bf8d0cb9f" }, { "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": "fd187c0126aae2724f9c66c319aafd06" }, { "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": "192817c5e55be863272cf8acd26f1d5b" }, { "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": "a62bf612678cf34a0885c9af697430a3" } ] }