scigemma_fine_tuned / ndarray-cache.json
NSTiwari's picture
Fine-tuned quantized Gemma 2b-it model.
b2c5500 verified
{
"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": "5c0cacbc67adf794f2d7c0e74511645e"
},
{
"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": "bf82afeae38ff8904939edc8f606ebfb"
},
{
"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": "e94909b78d3797e3237fde6009b79171"
},
{
"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": "73e9675eba85973d85ee977b23882cd3"
},
{
"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": "8b1989ed265127cd49dadb23205b8b28"
},
{
"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": "d75f7048d6f0783211efb85cceae847f"
},
{
"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": "725b70f5d13efb87584fca5a585ca0f1"
},
{
"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": "975c6c903fef182d0eb9e745dfaa7a97"
},
{
"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": "624532c62b41312f0bdf047a7d58eca5"
},
{
"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": "d71ebe204bcdd19c422ed5213fe05f9d"
},
{
"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": "5984e9eeb3450841e5dad42735fb2a20"
},
{
"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": "9f19029373e2abb3f05e83fd6d4130fa"
},
{
"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": "6a8827cec0dab8dd956d9835de38aa09"
},
{
"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": "fecaf1f5818a470e3fdafe7f91cc3dfd"
},
{
"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": "d8a2e72b8f402266b6d607cd83012c34"
},
{
"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": "d710aedbea23cb9b6650802066bdff22"
},
{
"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": "dbc1521879ff4a76866c083c6128052d"
},
{
"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": "46d7717c5bd5f8110cf430d44504a1df"
},
{
"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": "e65ceb0c2a50af902bae61fe6474fef7"
},
{
"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": "704e3f1a3305600b739b2931e2709142"
},
{
"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": "239bf3c3d51a136c59e163daec91fe65"
},
{
"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": "d8343cac3e0553a357cb78470ba84541"
},
{
"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": "35aec13b299fa0e01df8cc2d272fe69e"
},
{
"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": "d279e418386091dd58d82485d5da8889"
},
{
"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": "f0d6358cfb24c299afd335b363852bb0"
},
{
"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": "efc00d433db0ff2802f73dd5d8571649"
},
{
"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": "8298d05ea908eac319a44645ea7ceb1e"
},
{
"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": "391c06405b169232f7da2952f129b883"
},
{
"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": "a666badecd8f11729efd50ddc3d90f1c"
},
{
"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": "feb3a1bfe54ee6bbf4fac34e052c2549"
},
{
"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": "d949d240638b07ec4a2f6fa2da6171d5"
},
{
"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": "ce703a257b4f784647001d83f1dc2ceb"
},
{
"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": "c56267370c693a025a851315d083aa6d"
},
{
"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": "8c74d57047ccdc0c1ae35257f4b1f282"
},
{
"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": "bc1d94748682c365507261498bf47391"
},
{
"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": "5cd48e6af9b4642da326692f524c2b42"
}
]
}