| { | |
| "metadata": { | |
| "ParamSize": 325, | |
| "ParamBytes": 3631664128.0, | |
| "BitsPerParam": 2.6739310072364444 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 211365888, | |
| "records": [ | |
| { | |
| "name": "lm_head.q_weight", | |
| "shape": [ | |
| 128256, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 211365888, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "41caf9f2bd46bf86efb2aa6cb9a40862" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ba826dbf642fdce3a8f2993b89be3f42" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d6e571625f48bfe2c7beac8f2b61d149" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29369856, | |
| "records": [ | |
| { | |
| "name": "lm_head.q_scale", | |
| "shape": [ | |
| 128256, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 26420736, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.30.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 26420736 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 26428928 | |
| } | |
| ], | |
| "md5sum": "851bc9d12e8790acf0202b00f51944db" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4cce95a10ab3e3747d3d4ecff1c2bd30" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4eb3c0dc76d59c34d7d7c4eb22230f94" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.30.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 12664832 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 13508608 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 23633920 | |
| }, | |
| { | |
| "name": "model.layers.31.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "a10070b2d2a0f48c3e8f935a2b45b186" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 211365888, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_weight", | |
| "shape": [ | |
| 128256, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 211365888, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d80dc1831b14d2e81a929d31cca5c4b8" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26420736, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_scale", | |
| "shape": [ | |
| 128256, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 26420736, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c1f24d995411196046619677d74c305a" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6318ea8630c99007a971bdf869f9b325" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d213b849d141f2482bb46b47dde3232a" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27856896, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.31.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24907776 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24915968 | |
| } | |
| ], | |
| "md5sum": "af203373cc0923284cac1e080ca4a572" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f8f7b29d7c9a8fbc1808204883732a9b" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e9ecb7cb18198168c9ea741a4677dc99" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "100e43858f8f926f3025f1a1238f2718" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "93c3da0ebdb4e86fac69a0d3b07fe52a" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "934b14950ab1e4376d0a3cbee42680ec" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "65c3f7180e3be89a9e06f814023bc7fd" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "145a61f2a17107acf2412d47e880b51d" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a75e66857d91a9a79acf75b4d53a0ddb" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "6168a5d48f972abc46ffe8be6b0f46d5" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7150c09bed6825220f8dd3640ae3e65c" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ceb3dd299893d4011dccfe44a407b74e" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "cb955d2de064d7a76558db39780aec80" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e184152ef58e4aaa7be2327347425e45" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "26535377d3ceafc171c8c8c4e98d48c6" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "f403acc11a3f9ba13717857fe3f30aae" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7dd68b28c2c5856bf33886a1b1e4b45e" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "05444c4e3d238eff48d8ee6488149cbe" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "7bc4700b44a22d7ef791d555b0528e9c" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d1756da884802c38a34d9d109da8d2e2" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "43f1c792b7e020dd8f9bf53b0f312dc7" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "a567ff7131685d3ec9fbf54d83ec3f2e" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "28540c7cbd12c396785d1e46b6c62496" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 30806016, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 24899584 | |
| } | |
| ], | |
| "md5sum": "552f0a9426ce2f1fbc34bf2259064896" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "aff843d9b3012640cf43c30104d5264e" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "94f8beaa2cb9f5ad344e3e179c92e7a4" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "50b9d24da08bcb8f2d9bc8d1c1187b39" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bdf2838194eb01107994f482698f2855" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "466aa2766723dc9c642b2e621a6dfa10" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "7cfe90225e477c6a4f783e5d1eb51581" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2d0e34ab2dce91a4471f408288131fae" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d4cf10baa12aaf69cd7185e558630378" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "72f0dba4a0dbad375f28713be2767a61" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0f4010b982bb4682aa9134988f126811" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ebf7df0aba2b171ac56c078470366b0e" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "e718f52e0dc86244089f4bd277875051" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5a0ae4ebfddfc8159433dcdc8d2a54fc" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c3b059a865c841ec19973061b0e7cf0b" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "5d50387dd4e29b5ff9ca1f1f78db8aeb" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "74ec227df1d857720b88d66b9e94eb42" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "dea2822504d16e2c7dea70fa39b66985" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "9db3a6db31a3dc3b065486ef623beea2" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c10d151f48c5a1e62e7ea5d3869d1b4d" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ac34816c49c66a1bf2ca7174b0b9ce48" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "2e30e0c7ab84dae4b7319f2bdbcc1c9b" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2b3cecd03b46810c515ba24a466b12e6" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eb6ebd736fc607d580fdf15c604e017c" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "4fafe30ee501244699f6a0efecab69fa" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "239b46a70bb986bd4eb1cac77e941364" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7028946826e7c543293f6d6f9f111d39" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "c6c42d015dca3439b3cd20ae641dedc8" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 30375936, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 29110272 | |
| } | |
| ], | |
| "md5sum": "cf6bebe4ad89def3e6a8a261ca8ff23e" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 31129600, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 6750208 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 7593984 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 7602176 | |
| } | |
| ], | |
| "md5sum": "8ec91d8780ea0fcbed238a7456768964" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bf430d6ba625ba68ce5e1c328639c99f" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29425664, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 2940928 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 2949120 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 2957312 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 26484736 | |
| } | |
| ], | |
| "md5sum": "a6ea54ff91611efbab9852b7cc16fe7e" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5faf904d45ed9a31032351b04e639ebd" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7e40ce6d184bf767479c9f0b4b71f160" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "4a6b5967031554ea7470a48d255f99bb" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5834a8213292005756e60432015bc69a" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 32391168, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 5922816 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 29450240 | |
| } | |
| ], | |
| "md5sum": "2904eb3cd6d7f795e7b0c21e727a3263" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a5f283846c1f3b99856e90c89e0a7780" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6fffc8d780b0197d6bf21e7b22e83378" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "d41b491bf00d370c11a5169a0d5a2204" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "95acca7452a506e54cae4a3c8e898615" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c824763d72949d5970de67ff6dd2c4a5" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "20295f107dbf7025739d142a2bb4527f" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2570529ebd445fc6274feef32cc36471" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "744fe6b5dfb9847dcb77f2582aea5265" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "531c0ca2e8e7f9c026ea887fb92efd4d" | |
| }, | |
| { | |
| "dataPath": "params_shard_80.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "72906d53280c626779d33a6c9fc25703" | |
| }, | |
| { | |
| "dataPath": "params_shard_81.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2b5ad794fc7a920764a7695cd4d4a0d0" | |
| }, | |
| { | |
| "dataPath": "params_shard_82.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "948e36b62167ee9c7aa8ddfd878a2604" | |
| }, | |
| { | |
| "dataPath": "params_shard_83.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5a412010bfbc7a61b2cf563a8ebe60e5" | |
| }, | |
| { | |
| "dataPath": "params_shard_84.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d0ff2a8788677abb7c49092573625de8" | |
| }, | |
| { | |
| "dataPath": "params_shard_85.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "58aa802b08220954083b9f331c3e4652" | |
| }, | |
| { | |
| "dataPath": "params_shard_86.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e1c32e5244e4c0886559518359e660be" | |
| }, | |
| { | |
| "dataPath": "params_shard_87.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "92a1dd254fce195ea015836bb908673a" | |
| }, | |
| { | |
| "dataPath": "params_shard_88.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "bae85d83806c48c77c796e41574c197f" | |
| }, | |
| { | |
| "dataPath": "params_shard_89.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "252bd0102d520ae0cfc39cabec276dc2" | |
| }, | |
| { | |
| "dataPath": "params_shard_90.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0f0b4a2d9ef6ae6f7a3f1f2a0c55aba3" | |
| }, | |
| { | |
| "dataPath": "params_shard_91.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "bae8e5cb606c5766ee1a15df47875b88" | |
| }, | |
| { | |
| "dataPath": "params_shard_92.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "63379a5675fab3a3210726e82a29c2d7" | |
| }, | |
| { | |
| "dataPath": "params_shard_93.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "94c68896d1f3ef3a93a85f311b680a83" | |
| }, | |
| { | |
| "dataPath": "params_shard_94.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.28.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "257568069303166143e6cc6eebeaea8d" | |
| }, | |
| { | |
| "dataPath": "params_shard_95.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cde5de08b6ef452be3701684de69c709" | |
| }, | |
| { | |
| "dataPath": "params_shard_96.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b29e2a64b31d7d3b3d9914cf7d2a6c03" | |
| }, | |
| { | |
| "dataPath": "params_shard_97.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.28.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.29.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "367d831f461a56eadd64157fd71554c1" | |
| }, | |
| { | |
| "dataPath": "params_shard_98.bin", | |
| "format": "raw-shard", | |
| "nbytes": 24899584, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.29.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| } | |
| ], | |
| "md5sum": "6b2a4642618f32fc372febbabaf9ddbc" | |
| } | |
| ] | |
| } |