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": 1028997120.0, + "BitsPerParam": 5.005716164416316 + }, + "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": "5db513de0eb96e5a714838b63f6daf14" + }, + { + "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": "b0ecd602b43fb3a52c7f90d366d2aac0" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 32186368, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 100352, + 64 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 12845056, + "byteOffset": 0 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 100352, + 64 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 12845056, + "byteOffset": 12845056 + }, + { + "name": "model.layers.0.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 25690112 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 31465472 + } + ], + "md5sum": "8d130f18941295b3c6579ca18cae8ebd" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.0.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.1.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "a47e2b50d819fbf7053885998ca6d2fd" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.1.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.10.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "c4af8a488aedadb2ee808ec708dd2270" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.10.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.11.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "a779bc60d6ea3c8a27aff453641a0c39" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.11.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.12.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "04a3165bd49f2c649893ca177e0ad055" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.12.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.13.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "0684d04820bd046eb45523062ff7d7d3" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.13.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.14.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "9a0684d8c950f07c73e995efdfef2b42" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.14.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.15.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "981913e48bf80770da298ac078227ced" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.15.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.16.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "ed85cae355530f72fb29caee929050dd" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.16.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.17.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "657684ed120ef225f5ff06d0e5028145" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.17.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.18.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "9f0ffdf8d97f0bbac3500daaa963ddc5" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.18.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.19.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "09b335ea82dd795481d2ac397abc5e3e" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.19.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.2.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "f11fccd060c7a530470354ba4d817664" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.2.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.20.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "d6840c74b9a52d50136f4cef0193a644" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.20.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.21.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "b03f7690b9b428c483660c1194c4cd55" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.21.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.22.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "04ed6cb0e32e5ea7505b880dca869ac8" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.22.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.23.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "aab736a1cb5908f421402a82cbba6c75" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.23.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.3.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "e6f4d23137511ef38c7c844baa372d3c" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.3.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.4.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "613afdcefcc0d3e22000e1fe8b6a6ab3" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.4.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.5.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "c92402f53f6e1cd876f22a244cd61006" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.5.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.6.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "d959bdeb77be948c531bd4e56f4f9192" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.6.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.7.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "b3b693d398c61c130a3a3288981a45a1" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.7.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.8.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "0aa1ad19a46cf47ba5bc39f1856ee924" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.8.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.layers.9.input_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 720896, + "byteOffset": 28209152 + } + ], + "md5sum": "7c8a608e2e1cb5da6c27ba7cdc8edd19" + }, + { + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 1441792, + "byteOffset": 11534336 + }, + { + "name": "model.layers.9.post_attention_layernorm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12976128 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 12980224 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.bias", + "shape": [ + 6144 + ], + "dtype": "float32", + "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": "float32", + "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": "float32", + "format": "f32-to-bf16", + "nbytes": 262144, + "byteOffset": 22171648 + }, + { + "name": "model.norm.bias", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22433792 + }, + { + "name": "model.norm.weight", + "shape": [ + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4096, + "byteOffset": 22437888 + } + ], + "md5sum": "68193aded8d766096d3f74fb18c799c7" + } + ] +} \ No newline at end of file