{ "metadata": { "ParamSize": 198, "ParamBytes": 3087428608.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 466747392, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 151936, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 466747392, "byteOffset": 0 } ], "md5sum": "fecf67195ad7c035b39a5b4b1c77facc" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "f01fe30dd4b66d59562cd7e350fe4688" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 27535360, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 3072 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 27528192 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 27531264 } ], "md5sum": "53ba56fbef3f358710c88b7094762ab3" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "87cd1576987924e553ea7ee2e7f19300" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "ddfbf20abada3bf31cc1294cbd2bbaa4" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "79b51572a280ed240e3f211a3d4d2c58" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "2816556bc4da221cb6a750ee2ece563f" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "15e2a91381e3ffcd35f6d2b11dc43693" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "246f21c55a225dcdcc5d87881bcb06b3" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.0.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.1.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.10.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "9db0eff55267cb68ef2f15c9d8921f66" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "389eb23cbcc8cdeb6cf0666c1c14716d" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "858ff0c7d7ef0468583b849c3c011533" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "1e76825b651f7617ac67e943d9ceef3e" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "2362cf24665a73b622c3f392bbab76ee" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "85e525d88ea7db0deb627ee1aa325d88" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "70a8d25f82c16b0c7a46f3148062fbc3" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.11.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.12.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.13.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "fa92d7ef0417b9ce1906c462ab24ffea" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "a881856ab5b7a115095f01b657d2a60b" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "d425ac3b47746585b8e097e41dfec7b2" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "ca9ef1c6914a179e652d00d2064e50ef" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "7b991ce3e80b73c3e355753a6a230dea" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "763efc5964c72d0f4dbba97e835a312f" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "a95da5ac965ef3acc6325c5835885dc5" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.14.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.15.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.16.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "5f942015a57b4111606653701b142a7f" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "13680242c8c7ab440e5b7b82282a8290" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "7b83dd8b4e0735e958ed5c8bb941ba7e" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "932245788f69d73fc5e4c8180f9a4044" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "2c62b527c4cbb5b01b90ef0e9b49c822" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "cb6357e5a698342b07c422e8fbaf9c36" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "00d73f236aea765533c6d52f87d7af97" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.17.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.18.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.19.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "7fd4e25e6520542170a8eb83dd34b808" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "0370a3b61e1104aade32736eed768f20" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "d8848dd503a0c9a67908fdf6138be7d2" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "06075d5146ba69e8df5531112f0f9e1b" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "3d3ef7a857a7c6fe81f5af14755b9ab4" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "83b82ceda7135499fc6b9c23be8ac81d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "0b9d95eebe1ead5366d33d19b6053dfa" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.2.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.20.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.21.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "03bef970c2cedd8d2eac438675f1df1b" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "08d613a9ff790412962fd12134ab3a1e" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "c1620922ea2373b51b87463527663182" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.24.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "e61a68e14bce574f00d6b15f6f1829ff" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "740fed33f6bf3df4c44b826d3f957144" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.25.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "c688dbbdc6f8edcf61a10ef62c003802" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "88def80b770c79315621af9521be59d8" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.22.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.23.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.24.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.24.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "2c606ba7d834795d0792741e2744b78b" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.26.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "9822ca4f53df7fdfd996cf932ca71e4c" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "ee1f23db1ec45e20fbde3a4221b65fbd" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.27.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "c52f61792ae29307aa852a321ff6f9f9" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "515ae8963ca3a8122e018f2a8fc13c95" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "4885a9b7a3a5939478bfe31cee3a5b28" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "7a09a1539e93c381c1a48fb995b6bbfd" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.25.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.26.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.26.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.27.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.27.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "42f20e01ea60ca0c560a6beac3595d37" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "a3e225fc984284ae73ce70439ea4909d" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "4d86a4ac8c5b1e0f6f38624a5ee0e7bf" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "5372e6b4fb297a19e1c9862127797e94" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "41b9625467615c755e3fdcd20ec4e53c" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "2f7cd67584bbecd1c184e87d0ee6ba06" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "69bf0fb11d59922a5369f782851407b2" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.3.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.4.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.5.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "47b60369b87e10f488935fb5f4c33ddb" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "6f92932c3dafdfd2d6b579f22644d950" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "6ccdaa66cc9db71bf6cb0a14457fd073" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "f5745c3c21c80053544dce266c7114dd" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "22bb273ed7496d6748489b7fe0b503fa" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 27525120, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 1536, 8960 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 27525120, "byteOffset": 0 } ], "md5sum": "21f7faf648e423db9aa908d3a558ef2a" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 55050240, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 17920, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 55050240, "byteOffset": 0 } ], "md5sum": "778c6c84bac2ed0e9c194a06c0c61bdd" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33060864, "records": [ { "name": "model.layers.6.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11013120 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11016192 }, { "name": "model.layers.7.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 11020288 }, { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 17311744 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22030336 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22033408 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22036480 }, { "name": "model.layers.8.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 22040576 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 28332032 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33050624 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33053696 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 33056768 } ], "md5sum": "ab7b46752eff1100c8eed4cd1269dfac" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 11013120, "records": [ { "name": "model.layers.9.self_attn.c_attn.weight", "shape": [ 2048, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 1536, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4718592, "byteOffset": 6291456 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11010048 } ], "md5sum": "563b659b7554e11e85fbb315b50edce0" } ] }