diff --git a/mlc-chat-config.json b/mlc-chat-config.json
new file mode 100644
index 0000000000000000000000000000000000000000..54dd509f59cca5bb8ed2fb242dd16781395705a7
--- /dev/null
+++ b/mlc-chat-config.json
@@ -0,0 +1,20 @@
+{
+ "model_lib": "GOAT-7B-Community-q4f16_1",
+ "local_id": "GOAT-7B-Community-q4f16_1",
+ "conv_template": "llama_default",
+ "temperature": 0.7,
+ "repetition_penalty": 1.0,
+ "top_p": 0.95,
+ "mean_gen_len": 128,
+ "max_gen_len": 512,
+ "shift_fill_factor": 0.3,
+ "tokenizer_files": [
+ "tokenizer.model"
+ ],
+ "model_category": "llama",
+ "model_name": "GOAT-7B-Community",
+ "conv_config": {
+ "stop_str": "\n\n",
+ "system": ""
+ }
+}
\ No newline at end of file
diff --git a/ndarray-cache.json b/ndarray-cache.json
new file mode 100644
index 0000000000000000000000000000000000000000..798c839e8b140b4598e747b4663223d0f3a63f12
--- /dev/null
+++ b/ndarray-cache.json
@@ -0,0 +1,4344 @@
+{
+ "metadata": {
+ "ParamSize": 327
+ },
+ "records": [
+ {
+ "dataPath": "params_shard_0.bin",
+ "format": "raw-shard",
+ "nbytes": 65536000,
+ "records": [
+ {
+ "name": "param_0",
+ "shape": [
+ 32000,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 65536000,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_1.bin",
+ "format": "raw-shard",
+ "nbytes": 33357824,
+ "records": [
+ {
+ "name": "param_1",
+ "shape": [
+ 32000,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192000,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_2",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 8192000
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_2.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_6",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_3.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_8",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_4.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_12",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_5.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_3",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_4",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_5",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_7",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_9",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_10",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_11",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_13",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_14",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_6.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_16",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_7.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_22",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_8.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_15",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_17",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_18",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_19",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_20",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_21",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_9.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_26",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_10.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_28",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_11.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_32",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_12.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_23",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_24",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_25",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_27",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_29",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_30",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_31",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_33",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_34",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_13.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_36",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_14.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_42",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_15.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_35",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_37",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_38",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_39",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_40",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_41",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_16.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_46",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_17.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_48",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_18.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_52",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_19.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_43",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_44",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_45",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_47",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_49",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_50",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_51",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_53",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_54",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_20.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_56",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_21.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_62",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_22.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_55",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_57",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_58",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_59",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_60",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_61",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_23.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_66",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_24.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_68",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_25.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_72",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_26.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_63",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_64",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_65",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_67",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_69",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_70",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_71",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_73",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_74",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_27.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_76",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_28.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_82",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_29.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_75",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_77",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_78",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_79",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_80",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_81",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_30.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_86",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_31.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_88",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_32.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_92",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_33.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_83",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_84",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_85",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_87",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_89",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_90",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_91",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_93",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_94",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_34.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_96",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_35.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_102",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_36.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_95",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_97",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_98",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_99",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_100",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_101",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_37.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_106",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_38.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_108",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_39.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_112",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_40.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_103",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_104",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_105",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_107",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_109",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_110",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_111",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_113",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_114",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_41.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_116",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_42.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_122",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_43.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_115",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_117",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_118",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_119",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_120",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_121",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_44.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_126",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_45.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_128",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_46.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_132",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_47.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_123",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_124",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_125",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_127",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_129",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_130",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_131",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_133",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_134",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_48.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_136",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_49.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_142",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_50.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_135",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_137",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_138",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_139",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_140",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_141",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_51.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_146",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_52.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_148",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_53.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_152",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_54.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_143",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_144",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_145",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_147",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_149",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_150",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_151",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_153",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_154",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_55.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_156",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_56.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_162",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_57.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_155",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_157",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_158",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_159",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_160",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_161",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_58.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_166",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_59.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_168",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_60.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_172",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_61.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_163",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_164",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_165",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_167",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_169",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_170",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_171",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_173",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_174",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_62.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_176",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_63.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_182",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_64.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_175",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_177",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_178",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_179",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_180",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_181",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_65.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_186",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_66.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_188",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_67.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_192",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_68.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_183",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_184",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_185",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_187",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_189",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_190",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_191",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_193",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_194",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_69.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_196",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_70.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_202",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_71.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_195",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_197",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_198",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_199",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_200",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_201",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_72.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_206",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_73.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_208",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_74.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_212",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_75.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_203",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_204",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_205",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_207",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_209",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_210",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_211",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_213",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_214",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_76.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_216",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_77.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_222",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_78.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_215",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_217",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_218",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_219",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_220",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_221",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_79.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_226",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_80.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_228",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_81.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_232",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_82.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_223",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_224",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_225",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_227",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_229",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_230",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_231",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_233",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_234",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_83.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_236",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_84.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_242",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_85.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_235",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_237",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_238",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_239",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_240",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_241",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_86.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_246",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_87.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_248",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_88.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_252",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_89.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_243",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_244",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_245",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_247",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_249",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_250",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_251",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_253",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_254",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_90.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_256",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_91.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_262",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_92.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_255",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_257",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_258",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_259",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_260",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_261",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_93.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_266",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_94.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_268",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_95.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_272",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_96.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_263",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_264",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_265",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_267",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_269",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_270",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_271",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_273",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_274",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_97.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_276",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_98.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_282",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_99.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_275",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_277",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_278",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_279",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_280",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_281",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_100.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_286",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_101.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_288",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_102.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_292",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_103.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_283",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_284",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_285",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_287",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_289",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_290",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_291",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_293",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_294",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_104.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_296",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_105.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_302",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_106.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_295",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_297",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_298",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_299",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_300",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_301",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_107.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_306",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_108.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_308",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_109.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_312",
+ "shape": [
+ 12288,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_110.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_303",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_304",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_305",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_307",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_309",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 18219008
+ },
+ {
+ "name": "param_310",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21037056
+ },
+ {
+ "name": "param_311",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 21045248
+ },
+ {
+ "name": "param_313",
+ "shape": [
+ 12288,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_314",
+ "shape": [
+ 4096,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_111.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_316",
+ "shape": [
+ 22016,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_112.bin",
+ "format": "raw-shard",
+ "nbytes": 65536000,
+ "records": [
+ {
+ "name": "param_323",
+ "shape": [
+ 32000,
+ 512
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 65536000,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_113.bin",
+ "format": "raw-shard",
+ "nbytes": 32071680,
+ "records": [
+ {
+ "name": "param_315",
+ "shape": [
+ 4096,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_317",
+ "shape": [
+ 22016,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_318",
+ "shape": [
+ 4096,
+ 1376
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_319",
+ "shape": [
+ 4096,
+ 344
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 2818048,
+ "byteOffset": 29229056
+ },
+ {
+ "name": "param_320",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32047104
+ },
+ {
+ "name": "param_321",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32055296
+ },
+ {
+ "name": "param_322",
+ "shape": [
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192,
+ "byteOffset": 32063488
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_114.bin",
+ "format": "raw-shard",
+ "nbytes": 9240576,
+ "records": [
+ {
+ "name": "param_324",
+ "shape": [
+ 32000,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 8192000,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_325",
+ "shape": [
+ 2048,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 524288,
+ "byteOffset": 8192000
+ },
+ {
+ "name": "param_326",
+ "shape": [
+ 2048,
+ 128
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 524288,
+ "byteOffset": 8716288
+ }
+ ]
+ }
+ ]
+}
\ No newline at end of file
diff --git a/params_shard_0.bin b/params_shard_0.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f716003a8a3d8459a86bc2e713ed5d67b3d4da34
--- /dev/null
+++ b/params_shard_0.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f496df5de29e4a5cf7041eccd420a5e72397fd016ebaa239ef00f37b6d56d0a
+size 65536000
diff --git a/params_shard_1.bin b/params_shard_1.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c09ab33dd47e2a89fb4f6d53f917577a2962fdde
--- /dev/null
+++ b/params_shard_1.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b69427e821dbb973a85b1068b8b02254ff03b305b4096c308d1513916307cb
+size 33357824
diff --git a/params_shard_10.bin b/params_shard_10.bin
new file mode 100644
index 0000000000000000000000000000000000000000..900e801ed3d1cadb5eddef53da4e8550d7692433
--- /dev/null
+++ b/params_shard_10.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b18b8d5c0a1f695ca98f846a545a0869854ae6a9437cabe2bc8e679ed455ec
+size 22544384
diff --git a/params_shard_100.bin b/params_shard_100.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ceabf04b6b84a99bafa0dd2ec90f2eb0dba2d44e
--- /dev/null
+++ b/params_shard_100.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36c8b54a017f787cb46bdecab259e4a727d6853391e7329524887493da07dec
+size 45088768
diff --git a/params_shard_101.bin b/params_shard_101.bin
new file mode 100644
index 0000000000000000000000000000000000000000..05e9e83ab92bf007bf9ea09ac93bf914db5fb7b2
--- /dev/null
+++ b/params_shard_101.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b14dfd558984732dfffdeb0b192d08c03c9c210dda88a5f0582129b11f6e92
+size 22544384
diff --git a/params_shard_102.bin b/params_shard_102.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2ab1aae70a77597b7658847ca52e59a91b20abb7
--- /dev/null
+++ b/params_shard_102.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f32e04f1a6775fa26a74eabc5294df9c0197d7ddaf581f555e263864c7cdba8
+size 25165824
diff --git a/params_shard_103.bin b/params_shard_103.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1a88fcc2f6ba78480e22a5cce58c5f010e188240
--- /dev/null
+++ b/params_shard_103.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f643995b78281182a7a830c755d6501d5d2f95e62d89c3bb9536e66750cdbe8
+size 32587776
diff --git a/params_shard_104.bin b/params_shard_104.bin
new file mode 100644
index 0000000000000000000000000000000000000000..39af7f585f7e5880c9f39e13d810006fdf8ad3a5
--- /dev/null
+++ b/params_shard_104.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebfb91141fc2c7939627326a3a33a8810eaf2c6d67da6bf3cf6bbe5d2988a65
+size 45088768
diff --git a/params_shard_105.bin b/params_shard_105.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a84b7315f556a900652cfff907fc1be2fa4128c7
--- /dev/null
+++ b/params_shard_105.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d3737637b71c8034a5fcb06bdc3b16ec017247f519e9fdd8fedcc3379d2245
+size 25165824
diff --git a/params_shard_106.bin b/params_shard_106.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3c3c2e55ad0dd359c800375778788d392e484901
--- /dev/null
+++ b/params_shard_106.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050b418ca1fffc910a1ba10495a5d64c9698c79c7c7ecb7912d13b0f12726915
+size 32063488
diff --git a/params_shard_107.bin b/params_shard_107.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8196d3e02e31f5c2010a4628531b3972c222196e
--- /dev/null
+++ b/params_shard_107.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d55eb1f9c2b4c8a4dd3827cf53fe92e248bc8655990bd30ba44cb95d63ca97
+size 45088768
diff --git a/params_shard_108.bin b/params_shard_108.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f467ddd14553ca6f02bc3ecb0324feacc9035abd
--- /dev/null
+++ b/params_shard_108.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6e081a264eee56147b9f282f51c7ab5d0351dcfd1b79997497e310730fa4b3
+size 22544384
diff --git a/params_shard_109.bin b/params_shard_109.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4acb03d51017c8d3ce64ed6eae72994666e3c7b6
--- /dev/null
+++ b/params_shard_109.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1b9c37382108b86475da6c1d6120c83061a81a0ee9bc356c51d89c53cd88de
+size 25165824
diff --git a/params_shard_11.bin b/params_shard_11.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e5118cd3da22b8369ae875c70bf2d54d64aeaaa6
--- /dev/null
+++ b/params_shard_11.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea41e74783aeb214713faaf4d7cfc7ca007246b227b2df8bcc88872fb688628
+size 25165824
diff --git a/params_shard_110.bin b/params_shard_110.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7ae0031b952e70f20c2c7b70ce8e070342f1991c
--- /dev/null
+++ b/params_shard_110.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30eb450e0e6f91ff462dcc686aaef3c2c6e6857fda794ab04b512f858c2b780b
+size 32587776
diff --git a/params_shard_111.bin b/params_shard_111.bin
new file mode 100644
index 0000000000000000000000000000000000000000..78573089aead8ce040fe7d445bff28362c424a7e
--- /dev/null
+++ b/params_shard_111.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334713314b94f84e5fb6fc11a69c86d11d705e9084bd824b72e3b8fa8842c45d
+size 45088768
diff --git a/params_shard_112.bin b/params_shard_112.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f832b7b1974333cabc106c9b6b1bcbc190d18a2
--- /dev/null
+++ b/params_shard_112.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ff6e42ba3551f6fa7c8ca7f2a902a9a7f3e5b286a366b30b834ef59b437913
+size 65536000
diff --git a/params_shard_113.bin b/params_shard_113.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f602136a7ed7e71588021f79710aa5e8aaa0bf7f
--- /dev/null
+++ b/params_shard_113.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b8c159220465c62dbf7eb7423b50389c17ec4d4f9ab5a23a8b7388010d0e20
+size 32071680
diff --git a/params_shard_114.bin b/params_shard_114.bin
new file mode 100644
index 0000000000000000000000000000000000000000..072aeb6b081f233ee016b3a038e636308f85455d
--- /dev/null
+++ b/params_shard_114.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab2e929d4afcd6f492cb750e60f778be3ca62b56388efed6947bb173461379b
+size 9240576
diff --git a/params_shard_12.bin b/params_shard_12.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b6e86e0350f42753645237b8fedc6a97247d4a8
--- /dev/null
+++ b/params_shard_12.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9c4e59a798e3914e8e8c32860726609976ceb6f63842b999c96767dba385dd
+size 32587776
diff --git a/params_shard_13.bin b/params_shard_13.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9684e8b853d193c6aab8e8168a7f0d9c53d40334
--- /dev/null
+++ b/params_shard_13.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248aaf1fa2326bf7e4465696b7e11dc59ac6407723e75687c7221adfbeb10984
+size 45088768
diff --git a/params_shard_14.bin b/params_shard_14.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2fde0773adca4483089c454456b8f6ac569c0173
--- /dev/null
+++ b/params_shard_14.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af37e1f738ea9cc72340cb052dbee32459293813cdeea377e134dde8cf0daf70
+size 25165824
diff --git a/params_shard_15.bin b/params_shard_15.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3062cc12c6290e2887241e3e6921c9cb488381ef
--- /dev/null
+++ b/params_shard_15.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b998bc81e143865e371337dcf3fb7fde3fb44247e40c44fbe07c0737b87ab29a
+size 32063488
diff --git a/params_shard_16.bin b/params_shard_16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..878a86eb880287d1a6531375dc7abae2ceb06c15
--- /dev/null
+++ b/params_shard_16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38535bb6799917ad20f59923a7e0f60b6310e1c77c826c1c1b4fe2daa8d4c3b2
+size 45088768
diff --git a/params_shard_17.bin b/params_shard_17.bin
new file mode 100644
index 0000000000000000000000000000000000000000..21d5016aa8f7d5df1191d185eaf219f5a8df5235
--- /dev/null
+++ b/params_shard_17.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa63cda5e8cf8ed7f097d7ac1bed45e348ed234c51042a26fe97f3ebbc8afa0
+size 22544384
diff --git a/params_shard_18.bin b/params_shard_18.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da71bd1ca8eef38d5a7c0d8a62d99ed77323d080
--- /dev/null
+++ b/params_shard_18.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f88b65f5bdcd2e42c8c28ddfe41802344589567602a755974f78f6ca57886f
+size 25165824
diff --git a/params_shard_19.bin b/params_shard_19.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7656bfb8b7a8385644fa4d561d2c9496ef560b64
--- /dev/null
+++ b/params_shard_19.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718bd7f1f0d1facbb4ca6cde5436d4f7373847b390872f312554da9b496b45d1
+size 32587776
diff --git a/params_shard_2.bin b/params_shard_2.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0e9dbbe6b5fc503288198b05e5e7b5939bc73668
--- /dev/null
+++ b/params_shard_2.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d37f6f5059a4b60453abd1d11f8096fb3f2d1625114e93ab524abb08f7242ef
+size 45088768
diff --git a/params_shard_20.bin b/params_shard_20.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e39ae18de1d68fe002b0e954ce7f31d0ecc77679
--- /dev/null
+++ b/params_shard_20.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97563550ac238ec369d122e16151f9e5ae2adfeed067ec20c7eb39f1533ac4f3
+size 45088768
diff --git a/params_shard_21.bin b/params_shard_21.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e3b53ab61f43b13393c98f7433fd2d18a6bc3e90
--- /dev/null
+++ b/params_shard_21.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6860b39d0d4872fb82af3e665c4367c1b735888e48d3ba848b47429c369f9ae
+size 25165824
diff --git a/params_shard_22.bin b/params_shard_22.bin
new file mode 100644
index 0000000000000000000000000000000000000000..021cc85c549ba8ea200a37c357722db117d803b4
--- /dev/null
+++ b/params_shard_22.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572d76b349f75f0ac4d760dd6ce90d6bf1ade38bd6ad9d80817e4349cad5a8c6
+size 32063488
diff --git a/params_shard_23.bin b/params_shard_23.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ccc8b3c244a72fb4ad0f862416d7f3645701678f
--- /dev/null
+++ b/params_shard_23.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ad96b8ce33a5798eaaedef9639ff97837fa22da21a5e0a25ada08cf8b152ed
+size 45088768
diff --git a/params_shard_24.bin b/params_shard_24.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8ae6673e959a5352f3b9ab2bda776fb9a6e2b358
--- /dev/null
+++ b/params_shard_24.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29c280f3094947077d37d806ab7e062d983d4ccd93891504a38f5200277c22c
+size 22544384
diff --git a/params_shard_25.bin b/params_shard_25.bin
new file mode 100644
index 0000000000000000000000000000000000000000..78121f57ab09cb39b7eed4be854cbe13d6b0dcc7
--- /dev/null
+++ b/params_shard_25.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ac1346c4ccca43b240667ac2ec577bfa845815fb5fe21132085febda873daa
+size 25165824
diff --git a/params_shard_26.bin b/params_shard_26.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ea3ff1a0557f94ad4b9ba1b996d45fa72a66e745
--- /dev/null
+++ b/params_shard_26.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56db944bbdc36cb35a704ef981cf4beedde3354e703e1bd1f1032da3e502ef5b
+size 32587776
diff --git a/params_shard_27.bin b/params_shard_27.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9a71e60d5be883898594a7716ebe03650f60933f
--- /dev/null
+++ b/params_shard_27.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c73caa7784c7a976bd485d85aa3f5193710e44a484874b8c2bf4ebf5bc9b08e
+size 45088768
diff --git a/params_shard_28.bin b/params_shard_28.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3af3f97bd35a3dfff6a7cdcd97eaf4ca7958aa71
--- /dev/null
+++ b/params_shard_28.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1029c8a3ea2b857b466edffb709e89701aa402582099e78e47b8915685a1c814
+size 25165824
diff --git a/params_shard_29.bin b/params_shard_29.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9764dff3d59a59466c30fc969f94e6984aef8f7e
--- /dev/null
+++ b/params_shard_29.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b687bef0037c52d84018444bc9a026323873d40a485c4fcd9218ca638ff071c
+size 32063488
diff --git a/params_shard_3.bin b/params_shard_3.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2d13d282a7028a471193b47206a550e0a3179948
--- /dev/null
+++ b/params_shard_3.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e62023c2d6c8189dc5e301a305ea580236c04b2d1a7866e973b4c20d9cae39
+size 22544384
diff --git a/params_shard_30.bin b/params_shard_30.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e05b870d05533994c64e1049c9d4d3c65ce38ed1
--- /dev/null
+++ b/params_shard_30.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49f1f47d3841ba4eb76ee6363cfeb087caeedfd2b8aa0aa2a314d8e92aecdcb
+size 45088768
diff --git a/params_shard_31.bin b/params_shard_31.bin
new file mode 100644
index 0000000000000000000000000000000000000000..83cfde053678e4fbe79c7c908da4924a5e776358
--- /dev/null
+++ b/params_shard_31.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4f7814f6f89bd82739f74efdf8e428397afa9bd962082c9a90147d371ef3c8
+size 22544384
diff --git a/params_shard_32.bin b/params_shard_32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd78ec4afa8423f85543e84734ede1ef5b5c56b8
--- /dev/null
+++ b/params_shard_32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8a40e125a9a9f0177f928737adef9e5bcff5652fdee464a7e7471867950b21
+size 25165824
diff --git a/params_shard_33.bin b/params_shard_33.bin
new file mode 100644
index 0000000000000000000000000000000000000000..50af0f9ea6dcf2da2cdf12a0cb8e296c5e13749e
--- /dev/null
+++ b/params_shard_33.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4386c69f09add369f13b11a23635d5eec94f6f870e58c75991b17854ee8bae4a
+size 32587776
diff --git a/params_shard_34.bin b/params_shard_34.bin
new file mode 100644
index 0000000000000000000000000000000000000000..67c71e0fbf172acdfb1aba6e4c293bc694bc4032
--- /dev/null
+++ b/params_shard_34.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efae17e1dc03c4c696849cb28b04651fcdfa8c2e8a14bbb85271895995cca89f
+size 45088768
diff --git a/params_shard_35.bin b/params_shard_35.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eed793f3ecd739d8339bad1dcfb0f547e6f1d71a
--- /dev/null
+++ b/params_shard_35.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009bbd500c03bdfd782504ec3309d3995cc037f5ec65314915a9dc38b8fc48e3
+size 25165824
diff --git a/params_shard_36.bin b/params_shard_36.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6bb79217ee3b36dd8cc5d904c5954a17e722a7a6
--- /dev/null
+++ b/params_shard_36.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617904b36744c5423515ab16a25a3b1bd2a4f31db057467a966718eacc7c0d18
+size 32063488
diff --git a/params_shard_37.bin b/params_shard_37.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c5f1179cc2236f206b9a980b6aa6bbf02ffc8ba
--- /dev/null
+++ b/params_shard_37.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd6470058c63dff094e7d8d856066d7f358aba805429f5beb6cee62ecb1e0eb
+size 45088768
diff --git a/params_shard_38.bin b/params_shard_38.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f83c2027e3b80029f68fbd78c23860b290c854c1
--- /dev/null
+++ b/params_shard_38.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9365a912635506e2c4492561e70bb3dbcdecefb22be739ebb3868f96f8ed5f
+size 22544384
diff --git a/params_shard_39.bin b/params_shard_39.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5d6e0811612bb0234a76cc7905cd500bef80bde9
--- /dev/null
+++ b/params_shard_39.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff9c1a151db3c8f57f4dae29c867ba9b88a525a3840e6822e2bb0276f3b604f
+size 25165824
diff --git a/params_shard_4.bin b/params_shard_4.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eba31bb987d7ca651594f9b693b2646c49fc5fab
--- /dev/null
+++ b/params_shard_4.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537024bfcc5d8b49a3b2bc07fd0e137d8c1f2101ca2097624db9108c3bf93c34
+size 25165824
diff --git a/params_shard_40.bin b/params_shard_40.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5c031a230367d1159799f58b424c0a20c6e6bc16
--- /dev/null
+++ b/params_shard_40.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7015f216b8355f6b09317e221fcb512587cb1d79591a3aec58145d082fb4a6
+size 32587776
diff --git a/params_shard_41.bin b/params_shard_41.bin
new file mode 100644
index 0000000000000000000000000000000000000000..daac53fc6d632d79af845e694ca9b031322dab68
--- /dev/null
+++ b/params_shard_41.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012a0e93e6c753459889b8e60dd0fca68c58ef71ec901c61f432cd790f7f1121
+size 45088768
diff --git a/params_shard_42.bin b/params_shard_42.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ed948231a323835c4d1229066a961d6434de8c20
--- /dev/null
+++ b/params_shard_42.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da85f31cf197899efb99d2b3fa05744bf78b9baca3825a7c15f572e5c46ecdaf
+size 25165824
diff --git a/params_shard_43.bin b/params_shard_43.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7cafca32412a9b2ba1c8ab3037a03d259d629561
--- /dev/null
+++ b/params_shard_43.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4814c23b00efb1d3277578dce3ee0f54012f5ab8c51cfb1d0c543aab33a86b2
+size 32063488
diff --git a/params_shard_44.bin b/params_shard_44.bin
new file mode 100644
index 0000000000000000000000000000000000000000..06760420b249dfb56614887e5b1681d26dfc22df
--- /dev/null
+++ b/params_shard_44.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f626863b8e4504ef1dbab315d40cbafafeab621dbdf3c5e260c4b19fbd6cf8fc
+size 45088768
diff --git a/params_shard_45.bin b/params_shard_45.bin
new file mode 100644
index 0000000000000000000000000000000000000000..70d3968e9125b889b5c7d2b3909315a231bafc50
--- /dev/null
+++ b/params_shard_45.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694eb21179517ca9e55f028459875d327a0632c5d7ee068e7f0915a7cf2479db
+size 22544384
diff --git a/params_shard_46.bin b/params_shard_46.bin
new file mode 100644
index 0000000000000000000000000000000000000000..693bdcd2716a5cc6b07ba80bf2a6c8d97663224f
--- /dev/null
+++ b/params_shard_46.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05571201e0086e2332584a0828ef76d08de2c955848f53b5d3789ac98c9372a
+size 25165824
diff --git a/params_shard_47.bin b/params_shard_47.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a284e74daab13e1e5cc6811a4dc2f01b60b6b01e
--- /dev/null
+++ b/params_shard_47.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e8ff8044aae3d7748572307dbfb9b4c973e393402ad6efa24101bb0a8f5072
+size 32587776
diff --git a/params_shard_48.bin b/params_shard_48.bin
new file mode 100644
index 0000000000000000000000000000000000000000..120c44675822f27ee6c26a4629c75b1121d58af9
--- /dev/null
+++ b/params_shard_48.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aceced0d8efaab1e6b18dc7b5587e6ecd1c5970780f580cf44770d0572d759e
+size 45088768
diff --git a/params_shard_49.bin b/params_shard_49.bin
new file mode 100644
index 0000000000000000000000000000000000000000..03dc50117fcfc56252d7031e8dacaea125fd8152
--- /dev/null
+++ b/params_shard_49.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6712693156a872eb70e50b745e3bef6322b150ee01c8477110d38185b8b0a445
+size 25165824
diff --git a/params_shard_5.bin b/params_shard_5.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9e60db7e8c20072480d5d6932f8f205f1780f6e3
--- /dev/null
+++ b/params_shard_5.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e809c16ccc6e1fe7b75d34830d3db29fe8efa4e71cece5d3858587cf4dca5c
+size 32587776
diff --git a/params_shard_50.bin b/params_shard_50.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7877231d8e0b8782e51328c61207e2e8ed321e99
--- /dev/null
+++ b/params_shard_50.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50926b39e5a9b4fb8077a9633a5f30c1420bf63b8ba3f5ebdf4e7dfb95a595aa
+size 32063488
diff --git a/params_shard_51.bin b/params_shard_51.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8b66b806069a382ba040d68ede2ad21db0b9f68
--- /dev/null
+++ b/params_shard_51.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123568765bbf41b81176fead1fcec4a14154ad9bc4e7f8ed503e7543597ae01f
+size 45088768
diff --git a/params_shard_52.bin b/params_shard_52.bin
new file mode 100644
index 0000000000000000000000000000000000000000..54d47d5505b250c336984f1c740d9a939b6b5b90
--- /dev/null
+++ b/params_shard_52.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce40dae500e8b46aa0f4ece9f65c777bf9f362e14ba441382e8b580788326aa3
+size 22544384
diff --git a/params_shard_53.bin b/params_shard_53.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c22a30ed5d179d9cff9e838b89730195b0934c1a
--- /dev/null
+++ b/params_shard_53.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e6cf7c4ae0de4beb961d026c3025c10690fdd27c5463dc23d9e7f7e85fec4c
+size 25165824
diff --git a/params_shard_54.bin b/params_shard_54.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dba648890129a8e7eb0815b214ce737f2c602189
--- /dev/null
+++ b/params_shard_54.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41eafa93a1d317776a8b51a6ed309ca05a80b96f289b38d1be77fb109fae6b2c
+size 32587776
diff --git a/params_shard_55.bin b/params_shard_55.bin
new file mode 100644
index 0000000000000000000000000000000000000000..960a3d8767d4863a1643e9b27b61bbb815e23d7e
--- /dev/null
+++ b/params_shard_55.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5e19722260d16d46f0bbe589f71a57158ec63843192ca94d326a63d7f10aa6
+size 45088768
diff --git a/params_shard_56.bin b/params_shard_56.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9cffaf965245887a7fb1779f465bb75945f4957c
--- /dev/null
+++ b/params_shard_56.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c56ce5da6f1524d001fc0070e8490aa842bde6d43c6c04d836f09ec7ed63b5a
+size 25165824
diff --git a/params_shard_57.bin b/params_shard_57.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9ad02314644217a427e346203347d5234134b6dc
--- /dev/null
+++ b/params_shard_57.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ce1c255940f67b8115bb2f54ee20189dce9a42b60a1e773153734687e4e8c9
+size 32063488
diff --git a/params_shard_58.bin b/params_shard_58.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1fccf74964799675f54724b02aa9ebcd2334e890
--- /dev/null
+++ b/params_shard_58.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9edeae5ae5874ad4723e2b3501443f84999809c6fa833908d65bb4854a03c2e
+size 45088768
diff --git a/params_shard_59.bin b/params_shard_59.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d16145cb399cb12b738facb6901d15e2a27f3f4a
--- /dev/null
+++ b/params_shard_59.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f2ec17d79b24bf739b10dfec085da34a9acad158aa0877740d97f862496fbf
+size 22544384
diff --git a/params_shard_6.bin b/params_shard_6.bin
new file mode 100644
index 0000000000000000000000000000000000000000..84d9c5ce10db93283be1f910941f127b28726dd5
--- /dev/null
+++ b/params_shard_6.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a494d59d414a077108f3b851a6226308ea29f5f8eeaf0538d37f622ec8d371b
+size 45088768
diff --git a/params_shard_60.bin b/params_shard_60.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a3f4787d9b2b3bba22a7476be3308b7a47e40884
--- /dev/null
+++ b/params_shard_60.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53771c79217c07418d4f6a1a0368fb36e8980db0cab3473e787f4fc1f2d469de
+size 25165824
diff --git a/params_shard_61.bin b/params_shard_61.bin
new file mode 100644
index 0000000000000000000000000000000000000000..636b1a24c9a17ee99e4e4962064b36826a6d4876
--- /dev/null
+++ b/params_shard_61.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de9fea2132709ad434aba443a9d3e4a42ccf73606d53c38c847c603a97aff8c
+size 32587776
diff --git a/params_shard_62.bin b/params_shard_62.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e1f8006dfdc26f115959678576e95e0fae9b7bd2
--- /dev/null
+++ b/params_shard_62.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349b3511e561157d0a15c56c01fe6ec0109e8b97a4ec3af23d4558dbef09c5d6
+size 45088768
diff --git a/params_shard_63.bin b/params_shard_63.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5c76d1a41fe86a0a68157fe2a80e21a2132a81a5
--- /dev/null
+++ b/params_shard_63.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c827405c105f1bb0179ff631a22079ea83b2a92eb88bccec2ff5d557008045
+size 25165824
diff --git a/params_shard_64.bin b/params_shard_64.bin
new file mode 100644
index 0000000000000000000000000000000000000000..03711311428f7728406503d2714443c45902f0d0
--- /dev/null
+++ b/params_shard_64.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0025b4610af39441d0e6f3351dcc3601b8c4144039d1b04c4c5d5440b29a70
+size 32063488
diff --git a/params_shard_65.bin b/params_shard_65.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d9b83e615272f58effdfffa267b5d7730233be40
--- /dev/null
+++ b/params_shard_65.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5300b60c78129f63a1079aac466914e50ff4b693891bab74084c64a16ba991b
+size 45088768
diff --git a/params_shard_66.bin b/params_shard_66.bin
new file mode 100644
index 0000000000000000000000000000000000000000..92fd64ea6dddb9763dbdb779983c1730934e5f2a
--- /dev/null
+++ b/params_shard_66.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23034c5e5400dcc1062892ebcc8e8367c468300d7cbc55765dfdb0e26d3df71b
+size 22544384
diff --git a/params_shard_67.bin b/params_shard_67.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f27fe74c8457054c68fc50e77950c7c223740791
--- /dev/null
+++ b/params_shard_67.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2df89d30f97320d697b8cedc700170838466f21169aedfa3c18a64e3cfcb74
+size 25165824
diff --git a/params_shard_68.bin b/params_shard_68.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8c5f4699f7c05f09492bef3184201786a26a4b1
--- /dev/null
+++ b/params_shard_68.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608a3a85b647cc7d9013aa36f67b38d0761137ee77744750ecdcadd734a896df
+size 32587776
diff --git a/params_shard_69.bin b/params_shard_69.bin
new file mode 100644
index 0000000000000000000000000000000000000000..866ad801f4ce420561f6a4fcb285e40846daf857
--- /dev/null
+++ b/params_shard_69.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913acd854fae1a56a22aba7008f6e22f3a2fff8a110323b8b48a19d22e47104b
+size 45088768
diff --git a/params_shard_7.bin b/params_shard_7.bin
new file mode 100644
index 0000000000000000000000000000000000000000..441ad49fd49e810eaf4f95d51c302fee4732e336
--- /dev/null
+++ b/params_shard_7.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a455e942b84154ae7bb463ed3067747b8ad5c698abd66e4c9f4a95786875ab
+size 25165824
diff --git a/params_shard_70.bin b/params_shard_70.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8478cf50a3b55560b15b9006ebe659a1ab314657
--- /dev/null
+++ b/params_shard_70.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd72daffd7f0d71f90e9ba6b9a6876555e52813c1e2b997f7dd7ac463f0dd11e
+size 25165824
diff --git a/params_shard_71.bin b/params_shard_71.bin
new file mode 100644
index 0000000000000000000000000000000000000000..29fd4351cb00e8ffd2fea0207d132728ebd7dcf9
--- /dev/null
+++ b/params_shard_71.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a1df2a2e3e4fa46cb74bbc5ae353f6c70887d07d1d9fcbf7d5ee109637c7a0
+size 32063488
diff --git a/params_shard_72.bin b/params_shard_72.bin
new file mode 100644
index 0000000000000000000000000000000000000000..96274f90eb956891e42f701505c964b784207463
--- /dev/null
+++ b/params_shard_72.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc090f51adca91e88a4c1941d77f1b0fa5f2b24ef779ceab6722ccee7b76307
+size 45088768
diff --git a/params_shard_73.bin b/params_shard_73.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4acd5a857fc681c63af42654e15b65427d66d148
--- /dev/null
+++ b/params_shard_73.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7ff352a9f1503721743785ea8a7563d22f9961ec2d32e8023078d3aa2ff5d8
+size 22544384
diff --git a/params_shard_74.bin b/params_shard_74.bin
new file mode 100644
index 0000000000000000000000000000000000000000..602ee09ad56aea90017bb005b021b9456f651a08
--- /dev/null
+++ b/params_shard_74.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6a88721d470997bd081395398dbad9828ebc63b0c0e6518c6a99dd31992545
+size 25165824
diff --git a/params_shard_75.bin b/params_shard_75.bin
new file mode 100644
index 0000000000000000000000000000000000000000..787719103ad3b01615eca0fbb6067be6bde8b2c6
--- /dev/null
+++ b/params_shard_75.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228af450ab260c58141a622a84464454ec2ed9be17317a67c72fab332dc160d8
+size 32587776
diff --git a/params_shard_76.bin b/params_shard_76.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ba2a8a22bf1b96103d742813aa833860a028d5c0
--- /dev/null
+++ b/params_shard_76.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879646b30f1bffdc5289bb860010e71419432d13c79667b0506ecce41bd1077c
+size 45088768
diff --git a/params_shard_77.bin b/params_shard_77.bin
new file mode 100644
index 0000000000000000000000000000000000000000..97a9917d20f290c44e32beadef79600c88f5e5e5
--- /dev/null
+++ b/params_shard_77.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3997de0e80a31dfd05dc5348db7365adc8ae0a351edb9bd7f6dd181777da0726
+size 25165824
diff --git a/params_shard_78.bin b/params_shard_78.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ab4742073b7f36ebc89d314690067221373685a
--- /dev/null
+++ b/params_shard_78.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06341c2dc69d08882bcd499cd54ff7c9b73d05c95eef52e679e176fe269e7717
+size 32063488
diff --git a/params_shard_79.bin b/params_shard_79.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2311d1555d0f15bccbc8f58721cb833add2acc7e
--- /dev/null
+++ b/params_shard_79.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac12fd3fd2722a2520625aa0004ffe8c8145439a73d545e9eddad4c190a76391
+size 45088768
diff --git a/params_shard_8.bin b/params_shard_8.bin
new file mode 100644
index 0000000000000000000000000000000000000000..758dec5b4317e8e9eb2d45eab257652cb716b49b
--- /dev/null
+++ b/params_shard_8.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5914b0b015fcc3d224f2856791af2c834e18a2ecaa70ad6fe36bf11665988a
+size 32063488
diff --git a/params_shard_80.bin b/params_shard_80.bin
new file mode 100644
index 0000000000000000000000000000000000000000..094d73558fa10ae3773312c76bdad2d64249b01c
--- /dev/null
+++ b/params_shard_80.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c399678583ab3afbd2527fcf9e4afb281f911e5085521c5dd6dafa631c47d06
+size 22544384
diff --git a/params_shard_81.bin b/params_shard_81.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a1ecba4b32e53db15dca9e656bb250478e3874b1
--- /dev/null
+++ b/params_shard_81.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c25bdd8e5ce7e32f487376d990577b189a820e76f3cca6859574dd0545b20e
+size 25165824
diff --git a/params_shard_82.bin b/params_shard_82.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8cd7081dc12c8c6b44d81db432fbd619921b244a
--- /dev/null
+++ b/params_shard_82.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8a4746d3c387d703beb49263ca9d09990544aeace438b30e7f9f8aed95857f
+size 32587776
diff --git a/params_shard_83.bin b/params_shard_83.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4d30e46ecb3dde2fce64c8fbe0a22a1b0111c6c9
--- /dev/null
+++ b/params_shard_83.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080ab408445a4d5de05bd6c9bb9b280e0b5e7ffb291943273bcccfe6443ef0f6
+size 45088768
diff --git a/params_shard_84.bin b/params_shard_84.bin
new file mode 100644
index 0000000000000000000000000000000000000000..07f3e14df883d969b4d8c612d09c5eb2f8895314
--- /dev/null
+++ b/params_shard_84.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749388640d1fd7b094d2d68c40f20d304e17843de21a74c8bb4d4890c4ed9e4b
+size 25165824
diff --git a/params_shard_85.bin b/params_shard_85.bin
new file mode 100644
index 0000000000000000000000000000000000000000..557c06ef2e16d0f253a80ed06019c7951fd59da9
--- /dev/null
+++ b/params_shard_85.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a081cfc37852fe13271bba4140486d19be7eea63804ce5847c9925f47c4a83
+size 32063488
diff --git a/params_shard_86.bin b/params_shard_86.bin
new file mode 100644
index 0000000000000000000000000000000000000000..18158c266d151511ac364e8ad692485ae660a74f
--- /dev/null
+++ b/params_shard_86.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad2f7b0bc37c8844bced8bb6119e460453be624d313a3b649b2f01ab8a0b3cc
+size 45088768
diff --git a/params_shard_87.bin b/params_shard_87.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6335edf3c1a28b44f9cc8428e1e0b63d18db2534
--- /dev/null
+++ b/params_shard_87.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51339721dcc5480fa163673bd1f65b53f68bb7fbcfeadeb3b89c3eaabd5d146b
+size 22544384
diff --git a/params_shard_88.bin b/params_shard_88.bin
new file mode 100644
index 0000000000000000000000000000000000000000..297d600a2487ce9df36afb6974bd393f37c54e95
--- /dev/null
+++ b/params_shard_88.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3704350e372f45225faeea30f2a6aaf044356ed92e0cef23babe1b188c0c6955
+size 25165824
diff --git a/params_shard_89.bin b/params_shard_89.bin
new file mode 100644
index 0000000000000000000000000000000000000000..600640e6a99b736d7de986ffdffdd1736b91e8b3
--- /dev/null
+++ b/params_shard_89.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade141c134fcdaa134e7995595f3bd1ef9705ed2228501b9be2002d8942e92e8
+size 32587776
diff --git a/params_shard_9.bin b/params_shard_9.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c1e58a0e43aab08ae7033d05e5743e20733eff8e
--- /dev/null
+++ b/params_shard_9.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acc10f1cbc761018b88d67d73a5c3e00697752a64d95ca563698517988829ce
+size 45088768
diff --git a/params_shard_90.bin b/params_shard_90.bin
new file mode 100644
index 0000000000000000000000000000000000000000..25e2aeda659893fc15088b2a9d2c5068a54369f6
--- /dev/null
+++ b/params_shard_90.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7455c494dd2ba1486b8563dec42616a9cb4d6f1ae4587f473e6dc1d22b88e4
+size 45088768
diff --git a/params_shard_91.bin b/params_shard_91.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f35a44d19ad64a5ca77314076d271bfdcde9f199
--- /dev/null
+++ b/params_shard_91.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bd9dfb83addf9c0bd959554310a6ade4a5eb6670995c624f52d7946c2b0d756
+size 25165824
diff --git a/params_shard_92.bin b/params_shard_92.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8683d006d8d933c1437173f521fcc9226500f197
--- /dev/null
+++ b/params_shard_92.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61830aba3abcd834485ac186c3090279d3e4e5cf92f375253143cf8e98ea2933
+size 32063488
diff --git a/params_shard_93.bin b/params_shard_93.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ed89b8fbe4661f41a85c7f3a10f49f2e34afa320
--- /dev/null
+++ b/params_shard_93.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b682d6ade73f4963a46bd4cc7f19953d36a9ae0a7f343ca7c54d852439181d
+size 45088768
diff --git a/params_shard_94.bin b/params_shard_94.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b4f8e84ac71ef5fd8ee73f785ec27bb9b507bf5
--- /dev/null
+++ b/params_shard_94.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69348437440128729026711dabd43475e89758a52d5d8c11dff47e0623f7a9d
+size 22544384
diff --git a/params_shard_95.bin b/params_shard_95.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5182a917abe5df1884bf8017f10ab4a459e66d13
--- /dev/null
+++ b/params_shard_95.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ccb708943ebec8a768285d6b0ca7d9b0fea2cf1e48f46405dc6be4b82f9f21
+size 25165824
diff --git a/params_shard_96.bin b/params_shard_96.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d70a4e1c5b2cdc56a947034246685216a74e9039
--- /dev/null
+++ b/params_shard_96.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d06549a023e30c0a884f4ae7c10f684f9f0108458829c8dcbded1f6fdf46bb0
+size 32587776
diff --git a/params_shard_97.bin b/params_shard_97.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1ae901ebb60991d8dc1c8ee5b77a7539baaec14d
--- /dev/null
+++ b/params_shard_97.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e560ee18d4343f4cbbd28d5c4982879f50c7d1dd09e01c1329e6cc22d2c304be
+size 45088768
diff --git a/params_shard_98.bin b/params_shard_98.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0cc4b42690bbc5ccbd592d3cf4f767f3e9f84ca1
--- /dev/null
+++ b/params_shard_98.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7bcebe8048904850c7db786af206a27ec6ac10991ee1564ff505f18e0c02905
+size 25165824
diff --git a/params_shard_99.bin b/params_shard_99.bin
new file mode 100644
index 0000000000000000000000000000000000000000..178e9a0fe93a20e49076a141317926ad10fa62d6
--- /dev/null
+++ b/params_shard_99.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce47673505df04367684580c13ccd81cffc5f9b622f55057408818b0c9b8e3b
+size 32063488
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9e72adb60a1e9065645bd61fb8fa22d3423037b5
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}