diff --git a/mlc-chat-config.json b/mlc-chat-config.json
new file mode 100644
index 0000000000000000000000000000000000000000..858637283c55050bc7384b9ded838bf840ef5016
--- /dev/null
+++ b/mlc-chat-config.json
@@ -0,0 +1,16 @@
+{
+ "model_lib": "vicuna-7b-v1.5-q4f16_1",
+ "local_id": "vicuna-7b-v1.5-q4f16_1",
+ "conv_template": "vicuna_v1.1",
+ "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": "vicuna-7b-v1.5"
+}
\ 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..26ff5046328ea2803025c331991f6b00c32e6cd0
--- /dev/null
+++ b/params_shard_0.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c107622e9416d54aa58fa5c98d55c66efbcaac7efd1e0d8b0f9582a2949c1a80
+size 65536000
diff --git a/params_shard_1.bin b/params_shard_1.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ab70d11537dfda7e70dd15e8e4a3a844ccee1a17
--- /dev/null
+++ b/params_shard_1.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a7d69e76b12fb65dd475af23c536eb4042498a3b0e467b2fad3e5df54e41f1
+size 33357824
diff --git a/params_shard_10.bin b/params_shard_10.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5eb1019c5f8b3a450f90bae6782a7d6856e1e326
--- /dev/null
+++ b/params_shard_10.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dec3d69871c0d9d556225b30fd94f757bc14fee6ab5d425b4347d38173e979
+size 22544384
diff --git a/params_shard_100.bin b/params_shard_100.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5ce7f0648d2764cc25f60da84a948b21ac5c2412
--- /dev/null
+++ b/params_shard_100.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f46e2d308e30394cf20fa92471b2cc20a1baed52c568a01bf8732565a856cf6
+size 45088768
diff --git a/params_shard_101.bin b/params_shard_101.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4a7289031b038b3ca5d7a98a51a854e17576f6da
--- /dev/null
+++ b/params_shard_101.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5752215a64c2e5613665a034fa8ad77624813bb14e8621115a66916757218f5b
+size 22544384
diff --git a/params_shard_102.bin b/params_shard_102.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f778ce0d901c9967941191844222e09680634066
--- /dev/null
+++ b/params_shard_102.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d3ce57cd18194dcf0fc405ca13dff40e3357566439cf2e1f0bbd365d9e18b2
+size 25165824
diff --git a/params_shard_103.bin b/params_shard_103.bin
new file mode 100644
index 0000000000000000000000000000000000000000..41a218354b410b04cfac96a1b331a1c3686124a4
--- /dev/null
+++ b/params_shard_103.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffe0791f2cb5583ec6503a60563a31b80fa2b4ea12547eeedca8bd9f5025790
+size 32587776
diff --git a/params_shard_104.bin b/params_shard_104.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ee41123f90e2eb49695f8f1bfa213cfc7831e7e6
--- /dev/null
+++ b/params_shard_104.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe5b1fcbe3a1b66d8fa0df5748f6734fa50a19e4e9b41d218186b576010fe26
+size 45088768
diff --git a/params_shard_105.bin b/params_shard_105.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f28ab5229a3270fe849333cbd9b135ffd18463a
--- /dev/null
+++ b/params_shard_105.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0056252e3e99c2f5594f0a8ba7aca68bc9871bc34d71eca899d363a4727ef8
+size 25165824
diff --git a/params_shard_106.bin b/params_shard_106.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cff7dc2d3de20f8b90ea65fb0c19fae776332c29
--- /dev/null
+++ b/params_shard_106.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ca5c8c9070835354c26d8564b8ccc7e2c4d3d90444c0a4ec801b8f3a628bcf
+size 32063488
diff --git a/params_shard_107.bin b/params_shard_107.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5de300a08118bd3ad27bc9024db0911e2e539025
--- /dev/null
+++ b/params_shard_107.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37e8bfc69c1a7a510ccb392d52e019fe0e2a03c63e6900f5dbbd4d2749cfb53
+size 45088768
diff --git a/params_shard_108.bin b/params_shard_108.bin
new file mode 100644
index 0000000000000000000000000000000000000000..925016b245c5cf68b3ac6b6052c604a492e274ba
--- /dev/null
+++ b/params_shard_108.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27767a29ab87dad13a405e5c814e9f3a94c0560ef762ac3832245caf1b424158
+size 22544384
diff --git a/params_shard_109.bin b/params_shard_109.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1669047c651fe69ab9456d5b31ade035fb57058e
--- /dev/null
+++ b/params_shard_109.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a7d3751c0e16b2079c970258e4b5449b72a97accf95acf5a564545c97d968f
+size 25165824
diff --git a/params_shard_11.bin b/params_shard_11.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7405e552fa8fcf4038c642e880f903b1d0dbe938
--- /dev/null
+++ b/params_shard_11.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b335b6abf2ee6441b579b6e54d7d19a2364b6268981d3b538acc202104307664
+size 25165824
diff --git a/params_shard_110.bin b/params_shard_110.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3945b22d6d7db353245195dd1f471bc1fc148ea0
--- /dev/null
+++ b/params_shard_110.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35e0dcc0250a239a6b76cc708c7715dab70df3d69a8e70765fc51d4cd04e24f
+size 32587776
diff --git a/params_shard_111.bin b/params_shard_111.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c3a3047809db3f2547c831883566a290a34a91cf
--- /dev/null
+++ b/params_shard_111.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc55b4a38921789f0f34dca9f172ff8d63c5d44b05a9b2e550fbb2e8e513b105
+size 45088768
diff --git a/params_shard_112.bin b/params_shard_112.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f242dc00ac922839c97bf60d3d6e2b04711e19e1
--- /dev/null
+++ b/params_shard_112.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18edc935e5d149d23be876ed8bb20069aec6182700a5a46b3b4188f58a41366e
+size 65536000
diff --git a/params_shard_113.bin b/params_shard_113.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0c086b9a03a4531b843f2a5d27fc07d450abfc2c
--- /dev/null
+++ b/params_shard_113.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb08bdd30ee97b96b8e753086ef7a3be2ec07549564be9a8225c582a721f810e
+size 32071680
diff --git a/params_shard_114.bin b/params_shard_114.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8c1270354c3f690402ff419b4c5ea3440f734925
--- /dev/null
+++ b/params_shard_114.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c284b710536b9d23051a6f2cd49003a86a7df38266234b9f470ba3e32bf49209
+size 9240576
diff --git a/params_shard_12.bin b/params_shard_12.bin
new file mode 100644
index 0000000000000000000000000000000000000000..546361cfd11ebd09b954fa3ba5847219d1ff11cb
--- /dev/null
+++ b/params_shard_12.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d770db8e64b443ad27781424bf16dca8f6624115b213651740506ae47edc9fcd
+size 32587776
diff --git a/params_shard_13.bin b/params_shard_13.bin
new file mode 100644
index 0000000000000000000000000000000000000000..56e900525fca913ecc83acaa54caf5d56d0b6dec
--- /dev/null
+++ b/params_shard_13.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60e9cfeb719ffd81d012d1758fd02ad53a00225b30b5878432a3e08b1062a4e
+size 45088768
diff --git a/params_shard_14.bin b/params_shard_14.bin
new file mode 100644
index 0000000000000000000000000000000000000000..680eb106d81481a4cbed4547134c1f0ba5223bc3
--- /dev/null
+++ b/params_shard_14.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05d9f2e1c2cc1c43a3314b63ecfc551a2ba0224bc314352ad81148d763b8eb9
+size 25165824
diff --git a/params_shard_15.bin b/params_shard_15.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ad1f47e2a581b3323f6fdf48cd6566062c30d121
--- /dev/null
+++ b/params_shard_15.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238d6f567b08420b9edcac10a4b9456a1c7492bb62a9a592eb3ad709de4226a6
+size 32063488
diff --git a/params_shard_16.bin b/params_shard_16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..732e267f573380692235229707f30bd0db5827b1
--- /dev/null
+++ b/params_shard_16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3075fd3bca74ee2b498ee38387ca9fd3189b7f5a6a20aeae8543fef2fe9cb99
+size 45088768
diff --git a/params_shard_17.bin b/params_shard_17.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3b65406a63373d8acca63ec3af07516512d49cb9
--- /dev/null
+++ b/params_shard_17.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283f538335a79aedcd94cef54ee32c1b5d049028bd074fb5182e56a4acfed777
+size 22544384
diff --git a/params_shard_18.bin b/params_shard_18.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d727f687227ee0d84b6b133537e7dd5ec393bf81
--- /dev/null
+++ b/params_shard_18.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfb53549261f4190739aacff91957bac1a1bd9d62faa75085ffa46aa0863fc0
+size 25165824
diff --git a/params_shard_19.bin b/params_shard_19.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9f72cf5f79b71813358642f9af3bd8f140a5c386
--- /dev/null
+++ b/params_shard_19.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520453e4bd66b874f2d9bc69e919e3737ef931250d5c00441bceb1899b3ffa4e
+size 32587776
diff --git a/params_shard_2.bin b/params_shard_2.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5d6b6d1e1c3f5d656ace109bcde5bca1d0bf5846
--- /dev/null
+++ b/params_shard_2.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036f4389c895e501bdccc17ead12d515b31b67b87d03bacf4aae51c80a073f6a
+size 45088768
diff --git a/params_shard_20.bin b/params_shard_20.bin
new file mode 100644
index 0000000000000000000000000000000000000000..41fb41e9d038776df49e391f55aaef483b93c8f6
--- /dev/null
+++ b/params_shard_20.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327cd5a8e2810dfee27c1f8a2bfd03f255cd61e1a8019d6d3606a841b0d15f63
+size 45088768
diff --git a/params_shard_21.bin b/params_shard_21.bin
new file mode 100644
index 0000000000000000000000000000000000000000..20de4000d53efd32cae32fd58617e5847a6cf31d
--- /dev/null
+++ b/params_shard_21.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110d1365ef6b7bf3470d77e7916359dd489daa83df57dfdd8ab7c2194169b82b
+size 25165824
diff --git a/params_shard_22.bin b/params_shard_22.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ba69ffe2572b816bd9f68d1274b6b4c9251b5b34
--- /dev/null
+++ b/params_shard_22.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eebdcecef4bb577dffe3f4da411d709b463339f2357e1c58f2740167e649909
+size 32063488
diff --git a/params_shard_23.bin b/params_shard_23.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8678f5658f36d276e5d3c9d68382ae7d392c9e3c
--- /dev/null
+++ b/params_shard_23.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b57137f90e97af91e84b203e27cf2e191a3d24350b56b968632be4ec2a14c2
+size 45088768
diff --git a/params_shard_24.bin b/params_shard_24.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3af1920d2bea4fe9673a35d14dd72073785b3c5e
--- /dev/null
+++ b/params_shard_24.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8458d79c09e690c15c91f22a26bb89be193d0e423fb2098eb2041db4bff617c9
+size 22544384
diff --git a/params_shard_25.bin b/params_shard_25.bin
new file mode 100644
index 0000000000000000000000000000000000000000..099dd5f0bb8ad2d9a545e43fa20ae83a70c2de0d
--- /dev/null
+++ b/params_shard_25.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a62e420600eae4f36f868ae5b30cf17f92ca73bc9c65cab8a758ff42c6ead1a
+size 25165824
diff --git a/params_shard_26.bin b/params_shard_26.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2ddf93cb564635ab60961933597adadbce4589dd
--- /dev/null
+++ b/params_shard_26.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1bf193bf0b39eda66be856bbf8d6c4d1ba4ba4f083130e4d4d083ffe68f0d62
+size 32587776
diff --git a/params_shard_27.bin b/params_shard_27.bin
new file mode 100644
index 0000000000000000000000000000000000000000..83f1507b5cb0d59bec6abfc5b743774fe52bce3e
--- /dev/null
+++ b/params_shard_27.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45925a9d1469e2227117f41f73930e7de9c61b965ed4dcbb6b75ac3a9535f818
+size 45088768
diff --git a/params_shard_28.bin b/params_shard_28.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b44cde4c8bd002d7a601bdc048dc6cdd808392f1
--- /dev/null
+++ b/params_shard_28.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b1f3a396b55bf6c3f06f358e3e38d4a0bf55b156d9428dc74085dc351eb748
+size 25165824
diff --git a/params_shard_29.bin b/params_shard_29.bin
new file mode 100644
index 0000000000000000000000000000000000000000..accabcabbfb76259271a7e3025c6a1e8f5f04f90
--- /dev/null
+++ b/params_shard_29.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c109ce2e607cc4b059dadb4ba29fa47ac40cde1d518e231a44525d14f9907780
+size 32063488
diff --git a/params_shard_3.bin b/params_shard_3.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c7ca5a5d329e8d38c96c7928e8044b40bfa3967f
--- /dev/null
+++ b/params_shard_3.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004b0d1f3c8a568f2369ba54820d8c85b23dee88daab9548bd41adc222cac7f4
+size 22544384
diff --git a/params_shard_30.bin b/params_shard_30.bin
new file mode 100644
index 0000000000000000000000000000000000000000..75653a293da60f8b7ba590db631eefb0a07ba0be
--- /dev/null
+++ b/params_shard_30.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0a2bf76d19ef9008c9288e7b6be2dd79ec92f58c1987f4902ce902af11c23a
+size 45088768
diff --git a/params_shard_31.bin b/params_shard_31.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3b1e42ebfd22cc722b36ca733c4f5a8b76686598
--- /dev/null
+++ b/params_shard_31.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cdde68c16667b2d1409b0406c58e45e25df9d586631e1d2d684fa40a4167a94
+size 22544384
diff --git a/params_shard_32.bin b/params_shard_32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..90b403adef8ddd39449068df1268d7a3d21e2dfd
--- /dev/null
+++ b/params_shard_32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6655a07c62a23e76feaf8f7e2629ed45615a70f50fa53525860da838c02f8ba5
+size 25165824
diff --git a/params_shard_33.bin b/params_shard_33.bin
new file mode 100644
index 0000000000000000000000000000000000000000..332f8143d30a6fb08ab07be28a3efcfa3f900803
--- /dev/null
+++ b/params_shard_33.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10459917152039d28ed225cb56151df2c08354920b2f895e3f43013b63d34c7
+size 32587776
diff --git a/params_shard_34.bin b/params_shard_34.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c8ad37f85f7de7a110756aaa1c4b41b28cbf0d8
--- /dev/null
+++ b/params_shard_34.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4859fbb790efefb8a7572c3b9753ab3822bb4558d42c84b803a1703176cab90
+size 45088768
diff --git a/params_shard_35.bin b/params_shard_35.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e77756aadb25602376ca456ecbf9d6ee2b606419
--- /dev/null
+++ b/params_shard_35.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:583b8c7ebeb2594fd43599e945296050dfb9bbbff7b4b544142d7f084f0f307f
+size 25165824
diff --git a/params_shard_36.bin b/params_shard_36.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c7f69a35c3077ad6a20bcfe7c812f4c3ce2e2a6c
--- /dev/null
+++ b/params_shard_36.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f467c913ecdb6d85653ac99df535f08471b9757aa9c49d38b9317c00addb4b54
+size 32063488
diff --git a/params_shard_37.bin b/params_shard_37.bin
new file mode 100644
index 0000000000000000000000000000000000000000..04b7c33df2f44bddb6cfafe3bf3a98fd503ab51c
--- /dev/null
+++ b/params_shard_37.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8abb533647cec2824ed43975c646b1a06056d8792cc922c4f40c2669d4a82a
+size 45088768
diff --git a/params_shard_38.bin b/params_shard_38.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c38b2eb460b870d2c2029c5df7015bcf30fcdf6
--- /dev/null
+++ b/params_shard_38.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08657a0037c06c5d70518b8cd879594f039112027252b59faf2fb2f759c41703
+size 22544384
diff --git a/params_shard_39.bin b/params_shard_39.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c76f140f53c8f62ae7632c5a77786e42a4223e09
--- /dev/null
+++ b/params_shard_39.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48962a6dc20f694f53e06770c0568528e12fa5c9a862f1d3d25a93abc3a5a03
+size 25165824
diff --git a/params_shard_4.bin b/params_shard_4.bin
new file mode 100644
index 0000000000000000000000000000000000000000..760bb5a2406dc24df311223504e6e509792ef519
--- /dev/null
+++ b/params_shard_4.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4757605d50b50b8c401b0659fc286e456b77c1f7b8a97644ae1b2149cc46fa42
+size 25165824
diff --git a/params_shard_40.bin b/params_shard_40.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a886cfa1d13d171abe5db49063498ca8ae179dce
--- /dev/null
+++ b/params_shard_40.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b42ea99f1e364efa4dc57b67a6551b874a43f3d9307e7f1bbd652e35be5425
+size 32587776
diff --git a/params_shard_41.bin b/params_shard_41.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ec7473a194a2ada8056eb61964259d7bd4bfaf46
--- /dev/null
+++ b/params_shard_41.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28448c2884c05eeaaec7f1c3be6ec692c64ac8f58ab204fd687e36e2e3b617a
+size 45088768
diff --git a/params_shard_42.bin b/params_shard_42.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9b84d0e0fc0ef2dc8a23104d8e74d4d4fa7f083c
--- /dev/null
+++ b/params_shard_42.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cd3e9b3b09cd9e55e6e0521db8e1cab71887b7fb548b5784d286713bd9570d
+size 25165824
diff --git a/params_shard_43.bin b/params_shard_43.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bec7d2183503223ffe986c7bd760ae8ba30f2c77
--- /dev/null
+++ b/params_shard_43.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c14cf3d02a55cd582bac54911b81d61e33b4bcb1554c6c867189378672ac52
+size 32063488
diff --git a/params_shard_44.bin b/params_shard_44.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b0ea9c8b84759d2c6fefacd8b32d3df5d7319e4
--- /dev/null
+++ b/params_shard_44.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e035717bb40a8563c1fbae038b5de89adfd97f300e982cd46fd0fc61bfe4de
+size 45088768
diff --git a/params_shard_45.bin b/params_shard_45.bin
new file mode 100644
index 0000000000000000000000000000000000000000..72e7719e551fb00b62290ff5e64d1e86a3467015
--- /dev/null
+++ b/params_shard_45.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b63aa686cc662452722865fa8e942cfb6ab4582a7c1b0edb7911011aefe7c31
+size 22544384
diff --git a/params_shard_46.bin b/params_shard_46.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d07cf9c4ef56257bddc167a131b3ca26640f3b96
--- /dev/null
+++ b/params_shard_46.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d802a0664cfcebeeefcea3ca549a9ce7b988261921f2f0ca771e8993aef367ad
+size 25165824
diff --git a/params_shard_47.bin b/params_shard_47.bin
new file mode 100644
index 0000000000000000000000000000000000000000..49024e5e59296a5bf62c5c5a5ba592210e3796f3
--- /dev/null
+++ b/params_shard_47.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99cf5d2d89d47f5b6f9475aeeedcd86593e4868e359da7f30e253cdd806b03c
+size 32587776
diff --git a/params_shard_48.bin b/params_shard_48.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d65c3fb5fc9e1d2df5a2ad6d1ed4a69d01e8bc9e
--- /dev/null
+++ b/params_shard_48.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28da7c580657b19223df63403f0b219219a74c04663842ccc0bf7d0c66af921
+size 45088768
diff --git a/params_shard_49.bin b/params_shard_49.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7d48c1f25cca1bc0984b06e571ba9f2bc78882bb
--- /dev/null
+++ b/params_shard_49.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9331675447763aba1bc3919c8efa707e574d87dcbb3f6c9a7701205d7bdcd5e9
+size 25165824
diff --git a/params_shard_5.bin b/params_shard_5.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9d70a83ce1f768e081fbd83e5b0de3468964477f
--- /dev/null
+++ b/params_shard_5.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71f4767c29e9b033b15964fab8f17b898323369a4c26397b5dcf050c677d22b
+size 32587776
diff --git a/params_shard_50.bin b/params_shard_50.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fec7ff1b03e6939aaa062c745cf9e34ef83bb622
--- /dev/null
+++ b/params_shard_50.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db7d9dd4c590d3db5f20d46b52ee1b035b917667cbeb24b63ccc4c65a1a0f3a
+size 32063488
diff --git a/params_shard_51.bin b/params_shard_51.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a0c03cdd651b804b3c5e9a8bf41f57dadf575b2d
--- /dev/null
+++ b/params_shard_51.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ea7dd0c83c133224f1be99ff54ee38a3e9280e1a3824df59e662c7ce1ee7d9
+size 45088768
diff --git a/params_shard_52.bin b/params_shard_52.bin
new file mode 100644
index 0000000000000000000000000000000000000000..875d12d428c4eb38554e1dbafe59c372f45c7c4c
--- /dev/null
+++ b/params_shard_52.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826705da24ba68b07507e228bc3cca0ed6f0f3fa81b1c9763c3764ef600399c8
+size 22544384
diff --git a/params_shard_53.bin b/params_shard_53.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ee269da9e676b39649efb8bc9c8ba99a8c426434
--- /dev/null
+++ b/params_shard_53.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314900d97c0fdc8cb4a9000b81456a5fbd492e4e67461dd48ae9919a0e8ed3f4
+size 25165824
diff --git a/params_shard_54.bin b/params_shard_54.bin
new file mode 100644
index 0000000000000000000000000000000000000000..679408781791fac399b8a4e8fe11b79abe842244
--- /dev/null
+++ b/params_shard_54.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5904345ee69894d2244338067cf504c4f60aeb1445f3e1e4e46fdf64fc1c9f4f
+size 32587776
diff --git a/params_shard_55.bin b/params_shard_55.bin
new file mode 100644
index 0000000000000000000000000000000000000000..739ae8a5dc36aa847dfdc10d267d431deedeacc8
--- /dev/null
+++ b/params_shard_55.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b48e776b86c3a82b853a6352b9fbd3d86ea4c7d0cf5947841d2346bd606781
+size 45088768
diff --git a/params_shard_56.bin b/params_shard_56.bin
new file mode 100644
index 0000000000000000000000000000000000000000..47f54a76989ca8744ccec6e3469d8cad55ce527b
--- /dev/null
+++ b/params_shard_56.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b492cdb6b6540f1f001cf13bda1746824f14485a8233e0fd6849324efc57b1a
+size 25165824
diff --git a/params_shard_57.bin b/params_shard_57.bin
new file mode 100644
index 0000000000000000000000000000000000000000..64eed97227edb9102abf657e67fac0e95b4dc6d2
--- /dev/null
+++ b/params_shard_57.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2c7fd593a3777934c9adfdce09bdf61ec05f8acad391fd9b9e70a7ea092597
+size 32063488
diff --git a/params_shard_58.bin b/params_shard_58.bin
new file mode 100644
index 0000000000000000000000000000000000000000..91822e3391dbe335acd400b42742f0cab0f6abad
--- /dev/null
+++ b/params_shard_58.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e137479e52c00144b9282778a103e665fdb3991faaf04dff698606cf77b014
+size 45088768
diff --git a/params_shard_59.bin b/params_shard_59.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7675e332d60868968a265559ce47b280b30bf27e
--- /dev/null
+++ b/params_shard_59.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80292b9a477e5dba5ddf727094f3e341fc3f370f15354e8e2f361b6567ccbdd7
+size 22544384
diff --git a/params_shard_6.bin b/params_shard_6.bin
new file mode 100644
index 0000000000000000000000000000000000000000..74c76461f428961044946f42ecd4d3b511a4ee08
--- /dev/null
+++ b/params_shard_6.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a34ea074faf3f61711385bc049784bdd4f1bb902fa22fd627c79a9978276350
+size 45088768
diff --git a/params_shard_60.bin b/params_shard_60.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a286248962cf30de4c088dea7bf7fa0048297bb8
--- /dev/null
+++ b/params_shard_60.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d509c3c64c7d36fc12a86c71b6c14ecc77e30093887974f79eed0f95dd5bcfbc
+size 25165824
diff --git a/params_shard_61.bin b/params_shard_61.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ede35d8c757ec8e4eb491f4fa2d7f2b53ea7749c
--- /dev/null
+++ b/params_shard_61.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bb832b1ec78b42ed5356bb590a06721c0b1370c8b8f0deeb4e23c994b38377
+size 32587776
diff --git a/params_shard_62.bin b/params_shard_62.bin
new file mode 100644
index 0000000000000000000000000000000000000000..095783fe9093570ce5b1d44be721e4f1dd9b75ea
--- /dev/null
+++ b/params_shard_62.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e35beec8a6d42a19ab3cfada9537e603bb1290b56ef1738519ddb6acd827c6
+size 45088768
diff --git a/params_shard_63.bin b/params_shard_63.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7f51532dafad707cc436c297ef8486b361ed9e61
--- /dev/null
+++ b/params_shard_63.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148e1947267582e0f8ec9556e926cf103f8de66fc0f9125799b12ed4f8515690
+size 25165824
diff --git a/params_shard_64.bin b/params_shard_64.bin
new file mode 100644
index 0000000000000000000000000000000000000000..14d07c81b79c54c27ac0693acf6aca104fcd9211
--- /dev/null
+++ b/params_shard_64.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662a5a7283d2bdf13d5247398f5aa9ac27f04bb75511ccb583c3de167b5ec9ae
+size 32063488
diff --git a/params_shard_65.bin b/params_shard_65.bin
new file mode 100644
index 0000000000000000000000000000000000000000..674cd9062c66a53246af363e2f1b616cb5996e19
--- /dev/null
+++ b/params_shard_65.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82f952e816b206c045131b55032ed5cc95d2a9b1d1e726aa9767eaa985f8555
+size 45088768
diff --git a/params_shard_66.bin b/params_shard_66.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d5551c0983c9e2cff2de91c51c4cf6f09eb31b48
--- /dev/null
+++ b/params_shard_66.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c30f34241b948bbf60e38cd2356abe47e37990a70e5658401c273cd4f92d225
+size 22544384
diff --git a/params_shard_67.bin b/params_shard_67.bin
new file mode 100644
index 0000000000000000000000000000000000000000..466b3c40cc5b26a517dab4bd58cce4a77ef3c976
--- /dev/null
+++ b/params_shard_67.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76582ec528694fe5e1934b7c97132a6a8dd34cb893a2adece2cb6df52bb97394
+size 25165824
diff --git a/params_shard_68.bin b/params_shard_68.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ae480e8bc26c25fc9b1feb86a641042f0d90cecb
--- /dev/null
+++ b/params_shard_68.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63995701d508c40163bc5174be0b7ce4294f6034f4bd6c552479c41b1b4360f
+size 32587776
diff --git a/params_shard_69.bin b/params_shard_69.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2015df89ba9c916acb79fd566e9ca57fc6ca10a1
--- /dev/null
+++ b/params_shard_69.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c831cf3074f7beb4670e7afff3f7e23108c773770cb6a076f891121719367cca
+size 45088768
diff --git a/params_shard_7.bin b/params_shard_7.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65bcf97357794188ec980d8120c1c88e5b08c50a
--- /dev/null
+++ b/params_shard_7.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50158edf419fe4f391fd5657c7c3db1e7908afb6761df08d72d442ab21af768f
+size 25165824
diff --git a/params_shard_70.bin b/params_shard_70.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ae491882f86a9f335e033894fd048ca61d19eb64
--- /dev/null
+++ b/params_shard_70.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d446670bcd85909a49d954d457282bb1428cb5d4074b53ce4e5caa8b5ef69c8
+size 25165824
diff --git a/params_shard_71.bin b/params_shard_71.bin
new file mode 100644
index 0000000000000000000000000000000000000000..603f3501fea61b33d22cd0077efaedbb51da6680
--- /dev/null
+++ b/params_shard_71.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22af4327a86191d0a2384304c4c274817e201cf2e4d0ab4813c8fa66807ea72
+size 32063488
diff --git a/params_shard_72.bin b/params_shard_72.bin
new file mode 100644
index 0000000000000000000000000000000000000000..57b59816d1e2318ea4d8c0c30a9aaefe3ca4dc09
--- /dev/null
+++ b/params_shard_72.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab011acb9d90884d3a48ca7d33293cedf10c294e0d6d4a88d714b9810746a9a0
+size 45088768
diff --git a/params_shard_73.bin b/params_shard_73.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d97da7e0c22e5347287b04383cf1387bb94efa51
--- /dev/null
+++ b/params_shard_73.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba8bd953673b4b9e6c198d126bb11332a24d578f450f28cc3d0adf768e0447e
+size 22544384
diff --git a/params_shard_74.bin b/params_shard_74.bin
new file mode 100644
index 0000000000000000000000000000000000000000..79ab965b9b8b87717a9020113c96a60f83f7458c
--- /dev/null
+++ b/params_shard_74.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7c035f4797e4b75e8c4b03d2c90002793366b979dab719f12c91cc99af3a11
+size 25165824
diff --git a/params_shard_75.bin b/params_shard_75.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7df6256d2b9c71acd3a15071a4763cf0545d69f2
--- /dev/null
+++ b/params_shard_75.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086e7c560ce74d9c271080f52cdf9b7bc3f38eef0f1e8bf2c48f706864fa6695
+size 32587776
diff --git a/params_shard_76.bin b/params_shard_76.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9df2d4b4ffa5c653b0d1aa97807479b76206e914
--- /dev/null
+++ b/params_shard_76.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5133df501314d3c9b3687b60333484e6b21699f3e7ae777e77b1c14c8aef72ab
+size 45088768
diff --git a/params_shard_77.bin b/params_shard_77.bin
new file mode 100644
index 0000000000000000000000000000000000000000..06efaa856a3e2165b84a64474fadd1d3e516d2b3
--- /dev/null
+++ b/params_shard_77.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1247c74fd18a30f1ba8d31464eee6d570c930782672fb59065f8d7788ef9cbe3
+size 25165824
diff --git a/params_shard_78.bin b/params_shard_78.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2e0b216d83dfc2d58e8ad17626a91055a9a38c5c
--- /dev/null
+++ b/params_shard_78.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4aeb6aaeb868ebb1fa8beb5169fc11f88d150a78b2d909710bde53a9a6ec80
+size 32063488
diff --git a/params_shard_79.bin b/params_shard_79.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fe2c588c0d4d78efd968b94665223f6afa81e327
--- /dev/null
+++ b/params_shard_79.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df8f9e94954c361de6dec1618d4b6627fe96caea363b533a04b7cba4126f005
+size 45088768
diff --git a/params_shard_8.bin b/params_shard_8.bin
new file mode 100644
index 0000000000000000000000000000000000000000..696627abc74ff5e4364c2b585d2ca8300df9bc02
--- /dev/null
+++ b/params_shard_8.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d47c999f91f3f1a6b1ab0516006917dcf67ba8c42667bf72edce23efb19c57a
+size 32063488
diff --git a/params_shard_80.bin b/params_shard_80.bin
new file mode 100644
index 0000000000000000000000000000000000000000..da0ea40efd7d84d1b007717932827f2f24e27d18
--- /dev/null
+++ b/params_shard_80.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c750ffbd3bfb61fd6953b4278606b9ffdf5f055cb7766b06e96cf6eeae42d03f
+size 22544384
diff --git a/params_shard_81.bin b/params_shard_81.bin
new file mode 100644
index 0000000000000000000000000000000000000000..991391ee99c68c29fc9b82dc6290d03fc9040bce
--- /dev/null
+++ b/params_shard_81.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811292060895c25c58f100ca93809c7d750cf8916a151bbd267566cbcacf7c02
+size 25165824
diff --git a/params_shard_82.bin b/params_shard_82.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd01e51beab20cc98a10229ee1425cc26e909f2a
--- /dev/null
+++ b/params_shard_82.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbcc0b3311cc10c4be5979cc18471ff3a47fd873bba4602539854823cc4edbcb
+size 32587776
diff --git a/params_shard_83.bin b/params_shard_83.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b40d49624249fb876f7b7f3bbc25e06c1861c54c
--- /dev/null
+++ b/params_shard_83.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f4e74f91625c19c57f591d147ccad0cd8a62a2cc4330fc4db24de3f8187382
+size 45088768
diff --git a/params_shard_84.bin b/params_shard_84.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ed4db646c1f7cef714f0e62daa6df12d88f1f634
--- /dev/null
+++ b/params_shard_84.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df5f65240861a7fe821b6ed31c0b5d4aa1b07b696910b84a1bec30bc2a01335
+size 25165824
diff --git a/params_shard_85.bin b/params_shard_85.bin
new file mode 100644
index 0000000000000000000000000000000000000000..db833ff0410353cf9d3b2d5ce5e03e62f369d88e
--- /dev/null
+++ b/params_shard_85.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e1e1b5634ed115e90d6411eb1e3211e9185e8bb185b17648d6e16b7ca2cef1
+size 32063488
diff --git a/params_shard_86.bin b/params_shard_86.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e2cd3906e7e1d37f9d04c59a6e6abc2b6963719d
--- /dev/null
+++ b/params_shard_86.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462483c14043d77648e6b8b001edd2215ba02ed03ba42574e162b7bc0d6cc1c6
+size 45088768
diff --git a/params_shard_87.bin b/params_shard_87.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4c6b7c771d49df522832b0320dc741dd4bc9b16
--- /dev/null
+++ b/params_shard_87.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4444513ef568d48ee788675e5c2db4bfb5da849f1007e08368697558bb3fc6a2
+size 22544384
diff --git a/params_shard_88.bin b/params_shard_88.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b247ad1c0a62ce24e0b2cfee73ea75d8b086d6bd
--- /dev/null
+++ b/params_shard_88.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0940ce3e748f3007592e4855d3360aadbd1a8fd02fe5f8aa66ff7f2faf9c38a4
+size 25165824
diff --git a/params_shard_89.bin b/params_shard_89.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8321331af4494f9f2abd796aab2a56c3877b9508
--- /dev/null
+++ b/params_shard_89.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:282b6bde00ac15ad70300e031fc99f413f8b7a1863c8aec7ecb2f109a78ce309
+size 32587776
diff --git a/params_shard_9.bin b/params_shard_9.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b98ca537f38c360da11d798be0955594a5d2fb8a
--- /dev/null
+++ b/params_shard_9.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0384b0979009d8b18d6ae09c584e50401cd84eecf52e2cc1d901a71e7904d5e
+size 45088768
diff --git a/params_shard_90.bin b/params_shard_90.bin
new file mode 100644
index 0000000000000000000000000000000000000000..797c4f4e101f3ac6548745b5773f1b2d44d8f899
--- /dev/null
+++ b/params_shard_90.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48bafc2aeff54a21a9a88c25d9e79c4a51526dc8316899ec08b4a620a11feb92
+size 45088768
diff --git a/params_shard_91.bin b/params_shard_91.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9f4bf15625647137e994434fe99cd5208b8c29d6
--- /dev/null
+++ b/params_shard_91.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44a310ffa03484d4aae839a1dcb4305c14f44d7b8296d89e4583ee9f8e773fc
+size 25165824
diff --git a/params_shard_92.bin b/params_shard_92.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bd35121c5a12969ad9de8a6cb7bc83de0ef7b7d0
--- /dev/null
+++ b/params_shard_92.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b6bd2b1e2fd3c47140ad1e2468077be759c60057df4b4ec620e9060eea505e
+size 32063488
diff --git a/params_shard_93.bin b/params_shard_93.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c12489375dec5b5235bc116756aff628f5d5610
--- /dev/null
+++ b/params_shard_93.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e9ed1ec39e1045b48463f31bff967997235d328d603a252899cc176707f022
+size 45088768
diff --git a/params_shard_94.bin b/params_shard_94.bin
new file mode 100644
index 0000000000000000000000000000000000000000..968d37fe952cf484ad97578070e6fc44b12b5fa2
--- /dev/null
+++ b/params_shard_94.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfe0f4fb3af29c69665cb0d69236a0417e519de6cc1527efd69f30d9a80f4bd
+size 22544384
diff --git a/params_shard_95.bin b/params_shard_95.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e06682b1b2064b6ed48f988820f11e4f8c30ab0
--- /dev/null
+++ b/params_shard_95.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fc7695fd62d57094fb3f568e5a925617719a0bd8bade4049e8cc7ea623f346e
+size 25165824
diff --git a/params_shard_96.bin b/params_shard_96.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aa18ac53a94b3565d8a7bf591af43e9226c0cb10
--- /dev/null
+++ b/params_shard_96.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffdc73de18b6e8ddfa9dba1e9ab70aaf1c9341abd629f59ace916d4075d49ae9
+size 32587776
diff --git a/params_shard_97.bin b/params_shard_97.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f4db069fd625d58c8a9f1ac62fa415b8713b7a47
--- /dev/null
+++ b/params_shard_97.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31830a3d7c17d2a55d690b40ddcba614f385df166eb446a20ede4e60bdee218e
+size 45088768
diff --git a/params_shard_98.bin b/params_shard_98.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5bf763ad0e4c956f8c21f3eddef22611cd5fca62
--- /dev/null
+++ b/params_shard_98.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f1669aea4b42a31e10640fca9a3ee66c61989e427b0042508f2684dd7b5f3b
+size 25165824
diff --git a/params_shard_99.bin b/params_shard_99.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1088edc10b22f835ea025a9767c6be8651b85a02
--- /dev/null
+++ b/params_shard_99.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3be531ad8486ed7e9fd690be60ed2b6982083a1bfc0edf1048f1cfa403b8f03
+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..508754bfb1263631e39be7a2cd3577f6b5657c16
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,35 @@
+{
+ "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": 4096,
+ "pad_token": null,
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}