diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,3119 @@ +{ + "metadata": { + "ParamSize": 269, + "ParamBytes": 1033572352.0, + "BitsPerParam": 4.501551474039708 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 155582464, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 151936, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 155582464, + "byteOffset": 0 + } + ], + "md5sum": "9878e5bf478114e1c2ef22229db36efb" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 155582464, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 151936, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 155582464, + "byteOffset": 0 + } + ], + "md5sum": "a2c1cf32d869f34f4ecc61ca2045d194" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 19447808, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 151936, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 19447808, + "byteOffset": 0 + } + ], + "md5sum": "895ca8417bf14390b9bde1f7ac6ca9b5" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 25792512, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 151936, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 19447808, + "byteOffset": 0 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 19447808 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 19451904 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 25088000 + } + ], + "md5sum": "1c149a88c23108c8b56e8667c8263291" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.0.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "bec352c37fc586010f9bdbde814015d6" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.1.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.1.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.1.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "c51ace5243458449d6dd83b25d8a86ec" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.10.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.10.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.10.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "6e480dfa993e570caa6905456d05cbbe" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.11.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.11.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.11.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "41f4ba4a0145917fce69384ed30f6d73" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.12.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.12.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.12.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "485db6d3292a64b0d031109a4b2cd756" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.13.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.13.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.13.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "d7aa41f528a79206cacfb3b564e1d8e8" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.14.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.14.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.14.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "05db0e11a4064c96d765eeb912925ac4" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.15.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.15.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.15.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "7ea1f57a6333b104c8ea78cf5faa12f6" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.16.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.16.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.16.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "4a32a050ef438c859c5713f5929f9bf4" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.17.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.17.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.17.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "e5fdf5c1bedb512abc0333a7229ed010" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.18.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.18.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.18.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "2e00a88372d361a1d0f2aaf4313a8cb6" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.19.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.19.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.19.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "058ab98134a49bcfc3038a18d909fc7e" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.2.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.2.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.2.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "a352b02593ad51338344b23328c11a79" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.20.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.20.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.20.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "223f412cbcbae5ee2adcdf06a612a189" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.21.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.21.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.21.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "bf13a8681ca02333dced68a560751baa" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.22.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.22.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.22.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "f5a5d78ab988d73162f9908aaab864b0" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.23.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.23.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.23.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "f91064ef434d6ec5f2665f763dba1177" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.3.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.3.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.3.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "f4cda4a72c64cbdbe38f0862697c1cf3" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.4.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.4.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.4.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "a2b2fc5df14bde53c72179c240fcb670" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.5.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.5.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.5.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "6cccacb854252e7026431d9f77254466" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.6.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.6.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.6.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "8383d44d104cc42d2877b24e310c9ead" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.7.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.7.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.7.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "089593d8609d8061c13cea0a8ff8c1d7" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 28479488, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.8.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.8.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.8.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + }, + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 2048, + 688 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5636096, + "byteOffset": 22138880 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 2048, + 172 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 704512, + "byteOffset": 27774976 + } + ], + "md5sum": "2c55b990841b1cfb4177a382467b3430" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 22138880, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 11008, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11272192, + "byteOffset": 0 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 11008, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1409024, + "byteOffset": 11272192 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12681216 + }, + { + "name": "model.layers.9.self_attn.c_attn.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12685312 + }, + { + "name": "model.layers.9.self_attn.c_attn.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12697600 + }, + { + "name": "model.layers.9.self_attn.c_attn.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 18989056 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 19775488 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 21872640 + }, + { + "name": "model.norm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22134784 + } + ], + "md5sum": "49bd802aff2865dd8f615f5592c28978" + } + ] +} \ No newline at end of file