diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,3601 @@ +{ + "metadata": { + "ParamSize": 318, + "ParamBytes": 925540352.0, + "BitsPerParam": 4.502434662621765 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 102760448, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 100352, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 102760448, + "byteOffset": 0 + } + ], + "md5sum": "2564c3be8fc0ee011b559f5fde7179e9" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 102760448, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 100352, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 102760448, + "byteOffset": 0 + } + ], + "md5sum": "10614abf12fbf53ebbc36f62fa52cccf" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 32186368, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 100352, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12845056, + "byteOffset": 0 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 100352, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12845056, + "byteOffset": 12845056 + }, + { + "name": "model.layers.0.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 25690112 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 25694208 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 25698304 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 31465472 + } + ], + "md5sum": "ae0506a728dcb87d382a460a3bdc79b6" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.0.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.1.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "983347874be3fdbe3fc6157f4eb93e86" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.1.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.10.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "3ab562632b408dc4c25636ae4fe9dac9" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.10.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.11.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "abd2b4998631f1c35cf4651848f815ba" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.11.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.12.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "14d0adc090812670174de1508287a17d" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.12.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.13.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "fa41e03ad194ddb950483580b65faeb1" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.13.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.14.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "3d194cdd4fdc5a011133054152cb11f1" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.14.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.15.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "b6428af714c24001e5db900fd31cb4b7" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.15.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.16.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "a526df80f91bd95ea29ed86c3b7a5be5" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.16.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.17.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "118b37f0eca475bfe756d586d3fed4e6" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.17.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.18.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "f307ad243f7271d6c913f254a8a22950" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.18.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.19.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "f00ea91ac4246195c585e927c209f7ab" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.19.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.2.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "c104b545e95951f05f0c9828a4f917ff" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.2.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.20.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "b339ca1747d1cf7bea26c2cef785e304" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.20.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.21.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "d37507260de195a5b318c1d78baff1d6" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.21.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.22.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "20d0866edddf75b1ee01a5771b98f6fd" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.22.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.23.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "524e473a5d90b2a429d148178bc542bf" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.23.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.3.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "3a938fd67a02daaed7e248aed6ca25ae" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.3.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.4.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "cc5842e1b40dcb357cbf7d5055a09e5c" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.4.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.5.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "7ecf09d6cb9ef527ca356d3f055b1cb1" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.5.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.6.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "277be9968a22dbec0869097b7cb9e0e3" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.6.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.7.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "c88a1627ac9f4f516da278fbbaeb9074" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.7.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.8.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "7a6e94e235fd521b65e955ae797ab000" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 28930048, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.8.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.9.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + }, + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 2048, + 704 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 5767168, + "byteOffset": 22441984 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 2048, + 176 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "4915cc12db817f70d75164e681a29095" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 22441984, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 11264, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 11534336, + "byteOffset": 0 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 11264, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.9.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 12288, + "byteOffset": 12984320 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6291456, + "byteOffset": 12996608 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19288064 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 2048, + 256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 2097152, + "byteOffset": 20074496 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 2048, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.norm.bias", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.norm.weight", + "shape": [ + 2048 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + } + ], + "md5sum": "06ff09f1d5fe4927c9dd9e6f5c400d6d" + } + ] +} \ No newline at end of file