gemma-3-1b-it-q4f32_1-MLC / ndarray-cache-b16.json
riczhou's picture
Upload folder using huggingface_hub
1bb38e7 verified
{
"metadata": {
"ParamSize": 471,
"ParamBytes": 625381888.0,
"BitsPerParam": 5.003625757510393
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 150994944,
"records": [
{
"name": "language_model.model.embed_tokens.q_weight",
"shape": [
262144,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 150994944,
"byteOffset": 0
}
],
"md5sum": "a1be36ed801a0dcea23dfb1401e1a120"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 33150976,
"records": [
{
"name": "language_model.model.embed_tokens.q_scale",
"shape": [
262144,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18874368,
"byteOffset": 0
},
{
"name": "language_model.model.layers.0.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 18874368
},
{
"name": "language_model.model.layers.0.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 18876672
},
{
"name": "language_model.model.layers.0.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 22857984
},
{
"name": "language_model.model.layers.0.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 23355648
},
{
"name": "language_model.model.layers.0.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 31318272
},
{
"name": "language_model.model.layers.0.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 32313600
},
{
"name": "language_model.model.layers.0.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 32315904
},
{
"name": "language_model.model.layers.0.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 32318208
},
{
"name": "language_model.model.layers.0.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 32320512
},
{
"name": "language_model.model.layers.0.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 32321024
},
{
"name": "language_model.model.layers.0.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 32468480
},
{
"name": "language_model.model.layers.0.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 32486912
},
{
"name": "language_model.model.layers.0.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 33076736
},
{
"name": "language_model.model.layers.0.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 33150464
}
],
"md5sum": "a1db6f9d50be516a9d6f48920d7172ab"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 31043840,
"records": [
{
"name": "language_model.model.layers.0.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 0
},
{
"name": "language_model.model.layers.0.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 589824
},
{
"name": "language_model.model.layers.0.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 663552
},
{
"name": "language_model.model.layers.0.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 811008
},
{
"name": "language_model.model.layers.1.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 829440
},
{
"name": "language_model.model.layers.1.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 831744
},
{
"name": "language_model.model.layers.1.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 4813056
},
{
"name": "language_model.model.layers.1.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 5310720
},
{
"name": "language_model.model.layers.1.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 13273344
},
{
"name": "language_model.model.layers.1.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 14268672
},
{
"name": "language_model.model.layers.1.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 14270976
},
{
"name": "language_model.model.layers.1.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 14273280
},
{
"name": "language_model.model.layers.1.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14275584
},
{
"name": "language_model.model.layers.1.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14276096
},
{
"name": "language_model.model.layers.1.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 14423552
},
{
"name": "language_model.model.layers.1.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14441984
},
{
"name": "language_model.model.layers.1.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 15031808
},
{
"name": "language_model.model.layers.1.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 15105536
},
{
"name": "language_model.model.layers.1.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.1.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 15695872
},
{
"name": "language_model.model.layers.1.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 15769600
},
{
"name": "language_model.model.layers.1.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15917056
},
{
"name": "language_model.model.layers.10.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15935488
},
{
"name": "language_model.model.layers.10.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15937792
},
{
"name": "language_model.model.layers.10.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19919104
},
{
"name": "language_model.model.layers.10.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 20416768
},
{
"name": "language_model.model.layers.10.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 28379392
},
{
"name": "language_model.model.layers.10.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 29374720
},
{
"name": "language_model.model.layers.10.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 29377024
},
{
"name": "language_model.model.layers.10.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 29379328
},
{
"name": "language_model.model.layers.10.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29381632
},
{
"name": "language_model.model.layers.10.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 29382144
},
{
"name": "language_model.model.layers.10.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 29529600
},
{
"name": "language_model.model.layers.10.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29548032
},
{
"name": "language_model.model.layers.10.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 30137856
},
{
"name": "language_model.model.layers.10.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 30211584
},
{
"name": "language_model.model.layers.10.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 30212096
},
{
"name": "language_model.model.layers.10.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 30801920
},
{
"name": "language_model.model.layers.10.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30875648
},
{
"name": "language_model.model.layers.10.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 31023104
},
{
"name": "language_model.model.layers.11.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 31041536
}
],
"md5sum": "6d8c328f60bd6d948c8b62a51644b681"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.11.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.11.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.11.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.11.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.11.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.11.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.11.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.11.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.11.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.11.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.11.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.11.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.11.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.11.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.11.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.11.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.11.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.12.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.12.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.12.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.12.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.12.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.12.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.12.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.12.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.12.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.12.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.12.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.12.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.12.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.12.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.12.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.12.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.12.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.12.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.13.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "85e5cf9ccb1784a2a2664862e9ef13d7"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.13.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.13.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.13.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.13.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.13.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.13.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.13.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.13.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.13.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.13.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.13.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.13.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.13.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.13.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.13.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.13.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.13.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.14.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.14.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.14.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.14.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.14.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.14.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.14.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.14.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.14.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.14.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.14.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.14.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.14.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.14.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.14.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.14.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.14.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.14.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.15.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "0c286e2663923a68de86c44c94b4c812"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.15.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.15.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.15.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.15.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.15.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.15.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.15.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.15.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.15.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.15.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.15.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.15.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.15.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.15.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.15.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.15.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.15.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.16.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.16.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.16.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.16.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.16.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.16.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.16.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.16.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.16.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.16.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.16.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.16.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.16.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.16.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.16.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.16.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.16.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.16.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.17.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "7fae6393e9b8e6376520b3c3a56a531d"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.17.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.17.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.17.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.17.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.17.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.17.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.17.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.17.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.17.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.17.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.17.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.17.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.17.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.17.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.17.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.17.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.17.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.18.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.18.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.18.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.18.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.18.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.18.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.18.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.18.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.18.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.18.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.18.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.18.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.18.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.18.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.18.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.18.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.18.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.18.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.19.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "4ba2d0eab62fe74f332ad28887428dee"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.19.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.19.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.19.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.19.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.19.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.19.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.19.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.19.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.19.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.19.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.19.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.19.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.19.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.19.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.19.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.19.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.19.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.2.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.2.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.2.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.2.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.2.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.2.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.2.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.2.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.2.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.2.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.2.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.2.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.2.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.2.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.2.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.2.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.2.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.2.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.20.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "203e0ec4d9d81c6dc50eb342bfb67b8b"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.20.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.20.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.20.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.20.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.20.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.20.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.20.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.20.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.20.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.20.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.20.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.20.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.20.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.20.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.20.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.20.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.20.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.21.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.21.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.21.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.21.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.21.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.21.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.21.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.21.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.21.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.21.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.21.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.21.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.21.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.21.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.21.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.21.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.21.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.21.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.22.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "c6d98dbf7fbbe7992ab5c63e081ea90c"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.22.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.22.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.22.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.22.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.22.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.22.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.22.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.22.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.22.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.22.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.22.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.22.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.22.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.22.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.22.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.22.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.22.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.23.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.23.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.23.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.23.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.23.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.23.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.23.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.23.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.23.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.23.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.23.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.23.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.23.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.23.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.23.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.23.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.23.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.23.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.24.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "c11a908d5344de31d09622da441493d8"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.24.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.24.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.24.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.24.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.24.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.24.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.24.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.24.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.24.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.24.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.24.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.24.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.24.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.24.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.24.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.24.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.24.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.25.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.25.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.25.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.25.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.25.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.25.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.25.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.25.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.25.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.25.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.25.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.25.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.25.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.25.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.25.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.25.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.25.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.25.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.3.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "0ffdcd4a84712161c18d64b561c325c3"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.3.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.3.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.3.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.3.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.3.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.3.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.3.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.3.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.3.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.3.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.3.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.3.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.3.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.3.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.3.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.3.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.3.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.4.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.4.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.4.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.4.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.4.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.4.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.4.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.4.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.4.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.4.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.4.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.4.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.4.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.4.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.4.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.4.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.4.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.4.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.5.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "51199f36da9de0947f3c81db2a4e5f95"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.5.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.5.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.5.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.5.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.5.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.5.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.5.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.5.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.5.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.5.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.5.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.5.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.5.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.5.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.5.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.5.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.5.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.6.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.6.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.6.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.6.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.6.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.6.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.6.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.6.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.6.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.6.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.6.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.6.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.6.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.6.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.6.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.6.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.6.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.6.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.7.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "5b7452e5d3e0927752124f31b26bc3f9"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 30212096,
"records": [
{
"name": "language_model.model.layers.7.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.7.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.7.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.7.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.7.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.7.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.7.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.7.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.7.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.7.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.7.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.7.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.7.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.7.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.7.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.7.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.7.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.layers.8.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
},
{
"name": "language_model.model.layers.8.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 15106048
},
{
"name": "language_model.model.layers.8.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 19087360
},
{
"name": "language_model.model.layers.8.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 19585024
},
{
"name": "language_model.model.layers.8.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 27547648
},
{
"name": "language_model.model.layers.8.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28542976
},
{
"name": "language_model.model.layers.8.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28545280
},
{
"name": "language_model.model.layers.8.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 28547584
},
{
"name": "language_model.model.layers.8.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 28549888
},
{
"name": "language_model.model.layers.8.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 28550400
},
{
"name": "language_model.model.layers.8.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 28697856
},
{
"name": "language_model.model.layers.8.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 28716288
},
{
"name": "language_model.model.layers.8.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29306112
},
{
"name": "language_model.model.layers.8.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 29379840
},
{
"name": "language_model.model.layers.8.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 29380352
},
{
"name": "language_model.model.layers.8.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 29970176
},
{
"name": "language_model.model.layers.8.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 30043904
},
{
"name": "language_model.model.layers.8.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 30191360
},
{
"name": "language_model.model.layers.9.input_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 30209792
}
],
"md5sum": "94df05394e46e36f1cb2dbcd0bb13948"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 15106048,
"records": [
{
"name": "language_model.model.layers.9.mlp.down_proj.q_weight",
"shape": [
1152,
864
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 3981312,
"byteOffset": 0
},
{
"name": "language_model.model.layers.9.mlp.down_proj.q_scale",
"shape": [
1152,
216
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 497664,
"byteOffset": 3981312
},
{
"name": "language_model.model.layers.9.mlp.gate_up_proj.q_weight",
"shape": [
13824,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 7962624,
"byteOffset": 4478976
},
{
"name": "language_model.model.layers.9.mlp.gate_up_proj.q_scale",
"shape": [
13824,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 995328,
"byteOffset": 12441600
},
{
"name": "language_model.model.layers.9.post_attention_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13436928
},
{
"name": "language_model.model.layers.9.post_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13439232
},
{
"name": "language_model.model.layers.9.pre_feedforward_layernorm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 13441536
},
{
"name": "language_model.model.layers.9.self_attn.k_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 13443840
},
{
"name": "language_model.model.layers.9.self_attn.k_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 13444352
},
{
"name": "language_model.model.layers.9.self_attn.k_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 13591808
},
{
"name": "language_model.model.layers.9.self_attn.o_proj.q_weight",
"shape": [
1152,
128
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 13610240
},
{
"name": "language_model.model.layers.9.self_attn.o_proj.q_scale",
"shape": [
1152,
32
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14200064
},
{
"name": "language_model.model.layers.9.self_attn.q_norm.weight",
"shape": [
256
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 512,
"byteOffset": 14273792
},
{
"name": "language_model.model.layers.9.self_attn.q_proj.q_weight",
"shape": [
1024,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 589824,
"byteOffset": 14274304
},
{
"name": "language_model.model.layers.9.self_attn.q_proj.q_scale",
"shape": [
1024,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 73728,
"byteOffset": 14864128
},
{
"name": "language_model.model.layers.9.self_attn.v_proj.q_weight",
"shape": [
256,
144
],
"dtype": "uint32",
"format": "f32-to-bf16",
"nbytes": 147456,
"byteOffset": 14937856
},
{
"name": "language_model.model.layers.9.self_attn.v_proj.q_scale",
"shape": [
256,
36
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 18432,
"byteOffset": 15085312
},
{
"name": "language_model.model.norm.weight",
"shape": [
1152
],
"dtype": "bfloat16",
"format": "raw",
"nbytes": 2304,
"byteOffset": 15103744
}
],
"md5sum": "9237f449ad127a98ae7f37d18b412d7e"
}
]
}