{ "metadata": { "ParamSize": 135, "ParamBytes": 2200096768.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "lm_head.weight", "shape": [ 32000, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "2c912eb53da81bf4ed798392c6dca9c1" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 32000, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "399f96b720d3722787e4b4c53153db38" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "fa34e6caf91e51df6af120a36c719b67" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 23076864, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 4096 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23072768 } ], "md5sum": "665b16451cd7819f9459d97fcd4b636f" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "37ef5fa415ad986ab51a66a416aa038f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "49ef987668ce623867490def5af22e42" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "1c03cee852f757a5effe5031f62d898d" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "e0c42e6afb9acc2f06493b4b7ea8b697" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "3919996e166c175913687b3011a638bf" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "17f611d549b98636fd7a2cc677eafaf7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "5546632bd7f9edcbbea1997360360f51" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "35b557a4c14190f9b1cd4f8766a7f98d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "c5b76239603150d360630794c8d00e51" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.11.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "eb45fd07423c9ef8bdd2594bfb82aadb" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "549207afa7495fd9633b2bcb505290da" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "5647a65140d6c8b4f4822d23503c8a0c" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "6adfbc4e603f8276d5955c143c88de13" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "208c2247e69e1af227cb0763f1585adf" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.13.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "e5a3358dbf6572e5f29eb0574a2710f8" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "3693cba59637b5c149ea328e75d65f10" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "f9b6be0eef3c969c9399ec2c19a86812" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "3bda08ef56d03fa0935cda8e62f577e8" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "5f214b1f00df2168b293c54b93f698da" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.15.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "02f1b4551f1f43ea9a9d3eaef08949c7" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "91a33e4116fcaf5f483a6af8a5c84d06" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "d9a62f0ab43e06c6ada7e8f33c0b2e9b" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "062d11c5e83c3ab3f29441999dff582a" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "12fb5e1c494c84a7956d41a25cdd1d7e" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.17.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "7c7cb40e5739912436dffe8f5415a653" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "e19364880512f131126e7385d9c32eac" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "64f981313696f188e4bd7478ef039125" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "432c244c8ec1a184ad618484d7cf897b" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "63271c6a96f05bc97bf159176e6d5589" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.19.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "cadfaa50f214b92d0c35d239543c61e4" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "33dc7e372670369500baae0a73e738e5" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "9c2ed598e4412ee933e673ef0606d300" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "d2f3b396661e2381677d102eedf9fec2" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "90560d68478e9aaf9ab18f7d565e2979" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.20.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "f7dad919d98f25f033bdb2f1e670213e" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "7058d133bf8c15defd0608f5cc39ecf5" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "8c9470bf89d281643a4f7ecfbceded3b" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "be1adb2bbb2b85b38ad3811d55eee72a" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "2a986af683615d0b0b832ccdd1c9d3d0" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "0630623a24b0ed117b9d082a40400a74" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "8cb5908d2c193dbb86a4af843ddbf324" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "f181953e69d8fd705c4e4f10ccf3001f" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "42d390f90d09a8f6b87cee627a11dde9" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "e96c76d0d8a633cb1021918c02edb71d" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.5.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "b14c43e394cb826b709dd5a5ed0edf0a" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "9a49c18e3ea67739ec061eba259675ec" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "fb02a48b192522544f1ecdbedd6c504e" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "354728bb842783df3121b3dd3c74be00" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "9b3b2574f33b956f3d048433cc527dfc" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 31465472, "records": [ { "name": "model.layers.7.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8392704 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31461376 } ], "md5sum": "d7766f4b6cf1ec4a102d3a8b1a512ab5" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 23068672, "records": [ { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 0 } ], "md5sum": "d8486986a2147c55770851dd04cf64bc" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "f0cbb90d4428b9815210b55ae2e12267" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29368320, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 10485760 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18874368 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18878464 }, { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 2560, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 18882560 } ], "md5sum": "551093d9636d08c36c4c4686750acd3d" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 8392704, "records": [ { "name": "model.layers.9.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 } ], "md5sum": "67f5257abaa2b15cd8d1ad64db9b66fb" } ] }