{ "metadata": { "ParamSize": 220, "ParamBytes": 3289030656.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 411041792, "records": [ { "name": "lm_head.weight", "shape": [ 100352, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 411041792, "byteOffset": 0 } ], "md5sum": "2b614121ac608955bf05a75a1fb4fb21" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 411041792, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 100352, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 411041792, "byteOffset": 0 } ], "md5sum": "cc4e64884938277c14cca26991ac454a" }, { "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": "c11c3b75b91623c2b8df6f80d1ced196" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "528e4d5592435bde22bf4c9d3c3b16d9" }, { "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": "76345507c76c7d71b600b241c4e34335" }, { "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": "21837e46df8f1b6e26a4889d86e9b0a6" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "2f392e6d3352ff67d66100b5b32ae194" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31514624, "records": [ { "name": "model.layers.0.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 4096 }, { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8192 }, { "name": "model.layers.0.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23076864 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 23080960 }, { "name": "model.layers.0.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 23085056 }, { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 23097344 }, { "name": "model.layers.1.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31485952 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31490048 }, { "name": "model.layers.1.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31494144 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31498240 }, { "name": "model.layers.1.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31502336 } ], "md5sum": "02fb68c84620f2d121a605770b873e29" }, { "dataPath": "params_shard_8.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": "0017e98728a17e4d5416cec44a5f765b" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1182fd7a238c42bd876b70d725f57c8b" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.10.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.10.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.10.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "3bbb094c59a9170dd1eb969e8f2b15b1" }, { "dataPath": "params_shard_11.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": "65eb84eabf435dc5576fd0a4c4c84c0c" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7dddfc1fd52b6e7bf6068555805670bb" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.10.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.11.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.11.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.11.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.11.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "9a5ec1fc7ae4318c965b82143dd318bc" }, { "dataPath": "params_shard_14.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": "6d38a309694e2344069c986fb2f0ef7b" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "879f354ba7cf9c7247e34cab10a1c8d3" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.12.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.12.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.12.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "283bd5ed1b2b87e48423ca33c99a6e9d" }, { "dataPath": "params_shard_17.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": "c1062b4c69b6bd3a145ce25d18957795" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "2810e4140792276fc31e8583e8a60e10" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.12.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.13.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.13.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.13.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.13.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "640d5f061f36193f2ee15c07987a41c8" }, { "dataPath": "params_shard_20.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": "c26e3069cc12f5e3b19a0d72fa5f2474" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0cfb4d7c98729f74e6b5b00880bacda2" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.14.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.14.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.14.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "4562836334b1fb763e0bfbe88adb2788" }, { "dataPath": "params_shard_23.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": "cc9f5addc4b4a11c4268bd709eeb50df" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "0b24e7b671242ca9c19b215b787a3087" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.14.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.15.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.15.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.15.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "46e3d063f645a8ee7086357a9ebd353e" }, { "dataPath": "params_shard_26.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": "f3bba928e40d7b960ab90aff7fc8cbc2" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4a7a4298d6154e218f852b2221b64f9a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.16.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.16.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.16.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "db4af24c368590c46ac31dc8c86cf133" }, { "dataPath": "params_shard_29.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": "b2d7047ddaa9ed72e844b18aeaeb7183" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d24fd73b9e57491bd723c74b6617f08f" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.16.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.17.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.17.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.17.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.17.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "44b3b5d5eac8b369fd1b4bf27110baef" }, { "dataPath": "params_shard_32.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": "a2424b0971408440c56178df1914922e" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7429065ee6b19c504c1c9b92f109512b" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.18.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.18.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.18.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "0c0f5863987ad58e2e2b86db03b445b1" }, { "dataPath": "params_shard_35.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": "2489ce3e375f82027fe5febbfeed1983" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "93775501d86dbda8d9895e05861bd0c0" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.18.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.19.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.19.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.19.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.19.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "b18c21f498f8849fa24d0214226c55dc" }, { "dataPath": "params_shard_38.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": "34649a5d9d27d45f76577d0f9a642839" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "96146a45178784345f639e222da4a509" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.2.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.2.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "dd80050e13e4a23d067b0c7f91935e55" }, { "dataPath": "params_shard_41.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": "c1c76a937a8a07ba9509eaedea2167cc" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e34f90deb11e1218dff195ce4ae7973c" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.20.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.20.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.20.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.20.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "3b9041cf4fd9e161d24ecbea97b1c70d" }, { "dataPath": "params_shard_44.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": "8f33835d2d1ae8bddbacacce1a655f91" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "dc1d7d7f8a2ddc06293751151b5fcba9" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.21.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.21.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.21.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "05e9f964d8f77fae55fff96145e8e90a" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "b277a1d759778dcdfbc7b7050adab11d" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "279df9314d1bc73a72047e8394039bdb" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.21.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.22.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.22.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.22.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "ca8ebbc4473e11c0614473c64cf617dd" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 46137344, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.weight", "shape": [ 11264, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 46137344, "byteOffset": 0 } ], "md5sum": "fe5dbc52e0b685d6121efbb5a0f8d88a" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "19a3d52e52021399762b0957e410f145" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.22.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.23.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.23.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.23.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "51ffcc0ae1f863809efceacdda4be42e" }, { "dataPath": "params_shard_53.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": "68fd7bb2b74fa56963d4f9b8b9bbda5e" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e36fb1536922b1786ae7acfced221911" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.23.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.3.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.3.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "c04d16f3bfdc7fafab75a6f838413137" }, { "dataPath": "params_shard_56.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": "b8c672b774bd5175f3019ae2c7afb6a7" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4a45e64c62fd09faf7b54321ba1acefd" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.4.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.4.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "e8b66857bddbf4537104cad5d803271d" }, { "dataPath": "params_shard_59.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": "7449d9bf4936ba28a421d332e7e6934b" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9b91df02444da0a81d40ea3d208ec412" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.5.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.5.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.5.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.5.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "88a266f0f27e6ac863ee1ec6186d4080" }, { "dataPath": "params_shard_62.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": "22f3fc979274b77126889f5b37d23c46" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "57fb8e889c469ee9e6d8daf1f5cb84d7" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.6.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.6.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.6.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "73634973b7866ea7fd621ad350f1007c" }, { "dataPath": "params_shard_65.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": "2f383be54f35bd2e738aad136ebdc71e" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3331a8959b7f31d3a77de4769166d78c" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.6.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.7.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.7.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.7.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "d90ee9aab4fd6037fb04ac1feaf0957b" }, { "dataPath": "params_shard_68.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": "79e1ec42ed698343fa37e1084abfe20e" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "986ddba3c38a0118f361b9288b542cfc" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 31485952, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.8.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.8.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.8.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "f370b9c6fc8be57eed453a5372856e76" }, { "dataPath": "params_shard_71.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": "ade413a9306504cfef692d7a8f3ccc0e" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.weight", "shape": [ 6144, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3a22fdec40cce5f89f76d17baed8b961" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 31485952, "records": [ { "name": "model.layers.8.self_attn.o_proj.weight", "shape": [ 2048, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.9.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 }, { "name": "model.layers.9.mlp.down_proj.weight", "shape": [ 2048, 5632 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23068672, "byteOffset": 8396800 }, { "name": "model.layers.9.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31465472 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31469568 }, { "name": "model.layers.9.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 31473664 } ], "md5sum": "6847a86a31c4ff025e9058d87cece7f2" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 8396800, "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.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8388608 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8392704 } ], "md5sum": "a920ed378e8acb6d5bc8310b1aed2078" } ] }