diff --git a/mlc-chat-config.json b/mlc-chat-config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f57faf13fbca321c20ed7660ddd436559bb6b9a1
--- /dev/null
+++ b/mlc-chat-config.json
@@ -0,0 +1,16 @@
+{
+ "model_lib": "vicuna-v1-7b-q4f16_0",
+ "local_id": "vicuna-v1-7b-q4f16_0",
+ "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-v1-7b"
+}
\ No newline at end of file
diff --git a/ndarray-cache.json b/ndarray-cache.json
new file mode 100644
index 0000000000000000000000000000000000000000..68264fa0985432eabb859265052e94ab4ea46fdf
--- /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": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 8192000
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_2.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_6",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_3.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_8",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_4.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_12",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_5.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_3",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_4",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_5",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_7",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_9",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_14",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_6.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_16",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_7.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_22",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_8.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_15",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_17",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_18",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_19",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_10.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_28",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_11.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_32",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_12.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_23",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_24",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_25",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_27",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_29",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_34",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_13.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_36",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_14.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_42",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_15.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_35",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_37",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_38",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_39",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_17.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_48",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_18.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_52",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_19.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_43",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_44",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_45",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_47",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_49",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_54",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_20.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_56",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_21.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_62",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_22.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_55",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_57",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_58",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_59",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_24.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_68",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_25.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_72",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_26.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_63",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_64",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_65",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_67",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_69",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_74",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_27.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_76",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_28.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_82",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_29.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_75",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_77",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_78",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_79",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_31.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_88",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_32.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_92",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_33.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_83",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_84",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_85",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_87",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_89",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_94",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_34.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_96",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_35.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_102",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_36.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_95",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_97",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_98",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_99",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_38.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_108",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_39.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_112",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_40.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_103",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_104",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_105",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_107",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_109",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_114",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_41.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_116",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_42.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_122",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_43.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_115",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_117",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_118",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_119",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_45.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_128",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_46.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_132",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_47.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_123",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_124",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_125",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_127",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_129",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_134",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_48.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_136",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_49.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_142",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_50.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_135",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_137",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_138",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_139",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_52.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_148",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_53.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_152",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_54.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_143",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_144",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_145",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_147",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_149",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_154",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_55.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_156",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_56.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_162",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_57.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_155",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_157",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_158",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_159",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_59.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_168",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_60.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_172",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_61.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_163",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_164",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_165",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_167",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_169",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_174",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_62.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_176",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_63.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_182",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_64.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_175",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_177",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_178",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_179",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_66.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_188",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_67.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_192",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_68.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_183",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_184",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_185",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_187",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_189",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_194",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_69.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_196",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_70.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_202",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_71.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_195",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_197",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_198",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_199",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_73.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_208",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_74.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_212",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_75.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_203",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_204",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_205",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_207",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_209",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_214",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_76.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_216",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_77.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_222",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_78.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_215",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_217",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_218",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_219",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_80.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_228",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_81.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_232",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_82.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_223",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_224",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_225",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_227",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_229",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_234",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_83.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_236",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_84.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_242",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_85.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_235",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_237",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_238",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_239",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_87.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_248",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_88.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_252",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_89.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_243",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_244",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_245",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_247",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_249",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_254",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_90.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_256",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_91.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_262",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_92.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_255",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_257",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_258",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_259",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_94.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_268",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_95.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_272",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_96.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_263",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_264",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_265",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_267",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_269",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_274",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_97.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_276",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_98.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_282",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_99.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_275",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_277",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_278",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_279",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_101.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_288",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_102.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_292",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_103.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_283",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_284",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_285",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_287",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_289",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_294",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_104.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_296",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_105.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_302",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_106.bin",
+ "format": "raw-shard",
+ "nbytes": 32063488,
+ "records": [
+ {
+ "name": "param_295",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_297",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_298",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_299",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_108.bin",
+ "format": "raw-shard",
+ "nbytes": 22544384,
+ "records": [
+ {
+ "name": "param_308",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_109.bin",
+ "format": "raw-shard",
+ "nbytes": 25165824,
+ "records": [
+ {
+ "name": "param_312",
+ "shape": [
+ 512,
+ 12288
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 25165824,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_110.bin",
+ "format": "raw-shard",
+ "nbytes": 32587776,
+ "records": [
+ {
+ "name": "param_303",
+ "shape": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_304",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 3145728
+ },
+ {
+ "name": "param_305",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 11534336
+ },
+ {
+ "name": "param_307",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 12582912
+ },
+ {
+ "name": "param_309",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 12288
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 3145728,
+ "byteOffset": 21053440
+ },
+ {
+ "name": "param_314",
+ "shape": [
+ 512,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 8388608,
+ "byteOffset": 24199168
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_111.bin",
+ "format": "raw-shard",
+ "nbytes": 45088768,
+ "records": [
+ {
+ "name": "param_316",
+ "shape": [
+ 512,
+ 22016
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 45088768,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_112.bin",
+ "format": "raw-shard",
+ "nbytes": 65536000,
+ "records": [
+ {
+ "name": "param_323",
+ "shape": [
+ 512,
+ 32000
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 65536000,
+ "byteOffset": 0
+ }
+ ]
+ },
+ {
+ "dataPath": "params_shard_113.bin",
+ "format": "raw-shard",
+ "nbytes": 32071680,
+ "records": [
+ {
+ "name": "param_315",
+ "shape": [
+ 128,
+ 4096
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 1048576,
+ "byteOffset": 0
+ },
+ {
+ "name": "param_317",
+ "shape": [
+ 128,
+ 22016
+ ],
+ "dtype": "float16",
+ "format": "raw",
+ "nbytes": 5636096,
+ "byteOffset": 1048576
+ },
+ {
+ "name": "param_318",
+ "shape": [
+ 1376,
+ 4096
+ ],
+ "dtype": "uint32",
+ "format": "raw",
+ "nbytes": 22544384,
+ "byteOffset": 6684672
+ },
+ {
+ "name": "param_319",
+ "shape": [
+ 344,
+ 4096
+ ],
+ "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": [
+ 128,
+ 32000
+ ],
+ "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..050fbd52478cbe255a96ddca25acc56ac6a07a53
--- /dev/null
+++ b/params_shard_0.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14152ef72809621788b0578a07933c90e95df563502082a52d96c20cca14c20
+size 65536000
diff --git a/params_shard_1.bin b/params_shard_1.bin
new file mode 100644
index 0000000000000000000000000000000000000000..466762a7b7d0c136d076df4296e0775bc2fe6a36
--- /dev/null
+++ b/params_shard_1.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b241d020cdaeaed80a77d294afbdecc4a472e9c9d971069cd8e13f059f141a59
+size 33357824
diff --git a/params_shard_10.bin b/params_shard_10.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a186571cb08a5466914544f50c97e33f25a42371
--- /dev/null
+++ b/params_shard_10.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5eef2a4e35e6477274a8c8b7dfec282350b832fc5adef211187dc9bde31ede
+size 22544384
diff --git a/params_shard_100.bin b/params_shard_100.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0b4e0dbc0593f5767e913dd63b659e9395fa6d61
--- /dev/null
+++ b/params_shard_100.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c84b7e1f5ae6b9ae6b7d45f66a0a4616f651ec96f8f12aa8e7d266d09faa5a
+size 45088768
diff --git a/params_shard_101.bin b/params_shard_101.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7ff7f6eeef8be8a31b4c9d535eb293a2c44deb11
--- /dev/null
+++ b/params_shard_101.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90380a804ab1ed6f2af77f2616365a94cd75e0890bb096ec7edb5330de0aafa0
+size 22544384
diff --git a/params_shard_102.bin b/params_shard_102.bin
new file mode 100644
index 0000000000000000000000000000000000000000..47697e970bd64c09ce9ff94e0a6fb4a00d9c4621
--- /dev/null
+++ b/params_shard_102.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4d2324c4cfd0655e2c8addaa972e233369bea51246bf7841674674e8bea4d8
+size 25165824
diff --git a/params_shard_103.bin b/params_shard_103.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9a677a50a77e55f311d5d55dd243284c8095ad2d
--- /dev/null
+++ b/params_shard_103.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1336ee2eb4ee62c5bebd5b51702d4d38f80ada2c44d1afc450f1fc66b075525d
+size 32587776
diff --git a/params_shard_104.bin b/params_shard_104.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3b39f0c509ea70591b763454c4936ebd1d71033f
--- /dev/null
+++ b/params_shard_104.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f495e8cb7dd0a364b135cda0a355a1348e9fe0e080e2d5d9865b592d874130a
+size 45088768
diff --git a/params_shard_105.bin b/params_shard_105.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cc09b9f87b8fb96f2bef51fc22f669eeea7ee2ac
--- /dev/null
+++ b/params_shard_105.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98d454e0974a410b0c80d0e8b20aa4190b3b47d2eff04cab815b0f4df146699
+size 25165824
diff --git a/params_shard_106.bin b/params_shard_106.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b9909730eff362bbcacc2fb6069e3062c07d4c2c
--- /dev/null
+++ b/params_shard_106.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2314316c1745b1e182040aad81fa5d45c9f15ac0ee4f4695e26641fe99e8d4c0
+size 32063488
diff --git a/params_shard_107.bin b/params_shard_107.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f71b313c9946accac838fdc86beae3545b266abc
--- /dev/null
+++ b/params_shard_107.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2cd7591d3246e0b7b67da4a15bfeafebc9f5bd19f4b1c3740caf86d33a4b00
+size 45088768
diff --git a/params_shard_108.bin b/params_shard_108.bin
new file mode 100644
index 0000000000000000000000000000000000000000..16db6a098be1012e3883fc56530d6c961cf4955a
--- /dev/null
+++ b/params_shard_108.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056587cbc7fa1e5231943f34b95cb47b2222a9f402c6665d26e5e286ac646b57
+size 22544384
diff --git a/params_shard_109.bin b/params_shard_109.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0877827f1af658cfdec4f130eff94e0245cdd576
--- /dev/null
+++ b/params_shard_109.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4daf89c7b2df09e62c983426b4da79094a0efff6c2d8d15fc3d2e6a10727874c
+size 25165824
diff --git a/params_shard_11.bin b/params_shard_11.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fcda41ccfcdb99531f32506f6c6394748f208fac
--- /dev/null
+++ b/params_shard_11.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a103b2fc05d511e4f96196d965a2545f6d1274be9c28652b2e83f77ed191bbce
+size 25165824
diff --git a/params_shard_110.bin b/params_shard_110.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7fe98d52eb881a0eb7162f1a1132c045deaaf570
--- /dev/null
+++ b/params_shard_110.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3edfd11c977447e472a31c652ca4e6e7f2922e44c72859bf356d7ddfc6b61e8
+size 32587776
diff --git a/params_shard_111.bin b/params_shard_111.bin
new file mode 100644
index 0000000000000000000000000000000000000000..840883de76c31e59ccc755d7551ad728d5e4ca5d
--- /dev/null
+++ b/params_shard_111.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c089d52350100585add1d96f37f735c10af8fb8e0823b27628890339d953f88d
+size 45088768
diff --git a/params_shard_112.bin b/params_shard_112.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c0bc7d1d023e38ed5fb834322b73c7f79b3c1785
--- /dev/null
+++ b/params_shard_112.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb38ca5d2a1eed46e4bc996c2ef1e744d940496b5dd1dc444d55ec6e8e215a7
+size 65536000
diff --git a/params_shard_113.bin b/params_shard_113.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ee0eb50da1e43c1f01446ba6e5cfadd21f47cfdd
--- /dev/null
+++ b/params_shard_113.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea573bc6a1654c565db69a02752cde9e505567192bea381f6a11bb80dc2dae8
+size 32071680
diff --git a/params_shard_114.bin b/params_shard_114.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b8ec6a1999c4af5629a2801dcc1ad83aa3d3b3ae
--- /dev/null
+++ b/params_shard_114.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daeff7f98a3a1a5b31a3e8036ddee05372ffb5334ef0eef34f5990d0402dcda7
+size 9240576
diff --git a/params_shard_12.bin b/params_shard_12.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e50cb939c54c74156dfc11e3ce623368f73c148c
--- /dev/null
+++ b/params_shard_12.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b69ca69d4cac65274d6bc4147ab97c9846c7e293926e575c1041ee4ba3f0b78
+size 32587776
diff --git a/params_shard_13.bin b/params_shard_13.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e92d9c2e310b3832fc371106e3459b735c98ecac
--- /dev/null
+++ b/params_shard_13.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb28a4d7675c18b92bfd099f0b627dff0a656d496330052f13af5df69e6e3949
+size 45088768
diff --git a/params_shard_14.bin b/params_shard_14.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8e6d88c1ee6e2aea8cecc53e359e8bf478505813
--- /dev/null
+++ b/params_shard_14.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c3c64bf6266324db290ac2723c7dd8c8916aaa1a8a10ae6e9f3f5e0f1c37d3
+size 25165824
diff --git a/params_shard_15.bin b/params_shard_15.bin
new file mode 100644
index 0000000000000000000000000000000000000000..84e0e297df388875422c0ad2f115457c6f3c5e3a
--- /dev/null
+++ b/params_shard_15.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84519c0994d4c6b5b28ca7762ea6b48a20e27a72ccf210fb149f43ccb9a8f61
+size 32063488
diff --git a/params_shard_16.bin b/params_shard_16.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8bc7e29611b1736b231ae17dbeeeb10c65df9b90
--- /dev/null
+++ b/params_shard_16.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fbbe4e7afa55e26f83f05bc49930a76cfec055e4922d4c5e99f39f1001d091
+size 45088768
diff --git a/params_shard_17.bin b/params_shard_17.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fd8646c4e2bfd0902076b013ed4f33112b8c5110
--- /dev/null
+++ b/params_shard_17.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ca1cfe29b2dff32813de05de4e10862a627fc7a94cda5fc37f36d37f8940ae
+size 22544384
diff --git a/params_shard_18.bin b/params_shard_18.bin
new file mode 100644
index 0000000000000000000000000000000000000000..516b64a935bd45110f3a24c214895a5c9f44d8db
--- /dev/null
+++ b/params_shard_18.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b32992ae160459eacca6831f9514d8cae8f6fbffc586b86c4932e342beebe65
+size 25165824
diff --git a/params_shard_19.bin b/params_shard_19.bin
new file mode 100644
index 0000000000000000000000000000000000000000..54cfd95ea88c0fa738153ad4891a06486e77d0cb
--- /dev/null
+++ b/params_shard_19.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a66f67ef9b8623fdb59d9d1c57179b1dd6e86fb68b94895ee3c0fec978506b4
+size 32587776
diff --git a/params_shard_2.bin b/params_shard_2.bin
new file mode 100644
index 0000000000000000000000000000000000000000..089146b1c97a01a315da9bf4f49b475d7b0d0d2c
--- /dev/null
+++ b/params_shard_2.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a767aab148b78da5848623be680bb1b3d7231584941e63004a986b6ebc480c
+size 45088768
diff --git a/params_shard_20.bin b/params_shard_20.bin
new file mode 100644
index 0000000000000000000000000000000000000000..019dc40b5189da6e2e2beaaf2c53953b510fcfb9
--- /dev/null
+++ b/params_shard_20.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8377deabd0a8af9837a98dd78afc7a99e7bf4fc9826f56bc32f420aa63de3a0d
+size 45088768
diff --git a/params_shard_21.bin b/params_shard_21.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2abb47d0d8da9aef3d4d5dee1c6990b7e138680c
--- /dev/null
+++ b/params_shard_21.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87db156669b5ffc225c1f2a106d462ceddd24b48b07e22fabef391d58e423e52
+size 25165824
diff --git a/params_shard_22.bin b/params_shard_22.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f9ef5bbfa0f0dec16725d34c207bbfafa495cb71
--- /dev/null
+++ b/params_shard_22.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d721825e339a965499bdef549885653530cb60722c092319762c5a02179a8fb
+size 32063488
diff --git a/params_shard_23.bin b/params_shard_23.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e859b6106878989dcf52af3c94605de75ff55821
--- /dev/null
+++ b/params_shard_23.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b6ceaa846a6f8c1503dea959fc7a1b1c3149033f4eff55819cf9ce2893ac12
+size 45088768
diff --git a/params_shard_24.bin b/params_shard_24.bin
new file mode 100644
index 0000000000000000000000000000000000000000..370f896f247347b6dcfffe6ae07ce0748951a255
--- /dev/null
+++ b/params_shard_24.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90aeec969cf7bf1af82f1293784e1267248c13e892567813bf816a9323c53405
+size 22544384
diff --git a/params_shard_25.bin b/params_shard_25.bin
new file mode 100644
index 0000000000000000000000000000000000000000..51e9fce07b03a1e871bba60c86e6b5d7d3f29e00
--- /dev/null
+++ b/params_shard_25.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6c7829975d7c6b3b8492f46a6a4601154f67a1141c5a37cc3642cf08311e3d
+size 25165824
diff --git a/params_shard_26.bin b/params_shard_26.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fd20110036ad4c4018c91dad7c1ea88b87220cfd
--- /dev/null
+++ b/params_shard_26.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bd1e643ff6521008c44af8651cc02fb9188bf6e3fc47563f3d791a4b91c06d
+size 32587776
diff --git a/params_shard_27.bin b/params_shard_27.bin
new file mode 100644
index 0000000000000000000000000000000000000000..10fe8cd6f63c28febc04200ce87be306fb74035c
--- /dev/null
+++ b/params_shard_27.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89be3fef70ea996e1c9e776346202d17c6333e8f32fa435b2adf9b574f4826a
+size 45088768
diff --git a/params_shard_28.bin b/params_shard_28.bin
new file mode 100644
index 0000000000000000000000000000000000000000..72d967f41be1b69f4b5fded5e87eb9bf6246839d
--- /dev/null
+++ b/params_shard_28.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e177ed65ac0a2aad6790fbedd8304340dd0337dfeadad19b88af1a45c9356803
+size 25165824
diff --git a/params_shard_29.bin b/params_shard_29.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a3819916e1d89b2f9ca5a4c09a83f40c739f509e
--- /dev/null
+++ b/params_shard_29.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c28057291ff5756d27862a3389b0736fa5834e5859cbac36bb733fa7139911
+size 32063488
diff --git a/params_shard_3.bin b/params_shard_3.bin
new file mode 100644
index 0000000000000000000000000000000000000000..46eb2f04ce693ae16250959f87688f5308cca615
--- /dev/null
+++ b/params_shard_3.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41ed627c1f5da60401ca748538e65838d1a154b0c65b67c59a01678a04d5d7d
+size 22544384
diff --git a/params_shard_30.bin b/params_shard_30.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fcdd7556118077cbdd409860b283c6e6641894bb
--- /dev/null
+++ b/params_shard_30.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6669d04ea688111e2130f39dedda6cd25771a5afa38d49b9e06a771c76bd63a
+size 45088768
diff --git a/params_shard_31.bin b/params_shard_31.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e9f3ef732a44ee423d5cb10193a45b655829e587
--- /dev/null
+++ b/params_shard_31.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0526b8690232a898e989c59ab080b2ef439064c4dc8eb5ffd61c4216dbbc291a
+size 22544384
diff --git a/params_shard_32.bin b/params_shard_32.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bed5b00e548f469ba62dbc71836f5d06f26611a2
--- /dev/null
+++ b/params_shard_32.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1553690257eeedd75adfadcb3362ccca57b443daeb084bc4856b16f8e68b04fa
+size 25165824
diff --git a/params_shard_33.bin b/params_shard_33.bin
new file mode 100644
index 0000000000000000000000000000000000000000..75178cb54eaf383a6f4c2aa8e040b2a6dab346f2
--- /dev/null
+++ b/params_shard_33.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07123e5a238f23f37c0b21b3496937c1324c1a719d405d1bf6d97334ec13bdaf
+size 32587776
diff --git a/params_shard_34.bin b/params_shard_34.bin
new file mode 100644
index 0000000000000000000000000000000000000000..33c368d288bc8906e5661546fbc99ccf1777c1c1
--- /dev/null
+++ b/params_shard_34.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462af5857c0133109eaa2849e58cb2101ee31cff7d9ef3e5105d7a6f736d525f
+size 45088768
diff --git a/params_shard_35.bin b/params_shard_35.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d146364bdd2efa0aa24fc92b2d053c9cbf95ff8e
--- /dev/null
+++ b/params_shard_35.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637d7d3a6bf4cecdcdeaf248da38ac6da85f0c6669e153aa2e4dfe7bdbc201b0
+size 25165824
diff --git a/params_shard_36.bin b/params_shard_36.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1d2db5e532c0386b66c5623d9f7bc7ae53a7380e
--- /dev/null
+++ b/params_shard_36.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1d26b4acae89fbfb5a9c7b71ad357b26761c7f3eaf6f963a903388db7c089b
+size 32063488
diff --git a/params_shard_37.bin b/params_shard_37.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8ebaeceb07c60699c1ce78b2b1bff013bb0b23e
--- /dev/null
+++ b/params_shard_37.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c728b48f5ccc82830223d258af55fe1247d4faf0a63248838ddc0e60c8b9153
+size 45088768
diff --git a/params_shard_38.bin b/params_shard_38.bin
new file mode 100644
index 0000000000000000000000000000000000000000..aa5166561b8a0aaf770fa3d3db3dfb0c6c212b73
--- /dev/null
+++ b/params_shard_38.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937c34d102291d92cef8c3179cdf3177c476d6333d65d44ced2c38caf0fb7b73
+size 22544384
diff --git a/params_shard_39.bin b/params_shard_39.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6eae118f0333bea9a01af5981631931a40e57cea
--- /dev/null
+++ b/params_shard_39.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eedd8acc57a1fbdbbf2ee3309a3451756490356555991912bf06a82d50517f08
+size 25165824
diff --git a/params_shard_4.bin b/params_shard_4.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8106cdb7a05c9f5c0c501fa7e2b6585c74dc8037
--- /dev/null
+++ b/params_shard_4.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4168c7ae402e95dce3d086ea652f7468d8b3944cc5f31d57c004356b71a0fb4f
+size 25165824
diff --git a/params_shard_40.bin b/params_shard_40.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d923fe3336fdf40347f704940fa1d89aa6c5e832
--- /dev/null
+++ b/params_shard_40.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d80a081e858f03481066b52382f793f977fca052a63c06473e7bee78a197e10
+size 32587776
diff --git a/params_shard_41.bin b/params_shard_41.bin
new file mode 100644
index 0000000000000000000000000000000000000000..594da3b64917ecb49ef18ac050d40b90a1ffdf60
--- /dev/null
+++ b/params_shard_41.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1ca924125c48ff883bff826ca2dd127c67567acd7c89c3482992609e06432b
+size 45088768
diff --git a/params_shard_42.bin b/params_shard_42.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8631f98546537da5ca5cc25abcc5a2049be05292
--- /dev/null
+++ b/params_shard_42.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70dbf8f8f08414ec2e4e1018eb2d1217b92e31634e370bc16c850041f13b43d2
+size 25165824
diff --git a/params_shard_43.bin b/params_shard_43.bin
new file mode 100644
index 0000000000000000000000000000000000000000..de8cd260ac59d60a8745a7dc3f428aece6977491
--- /dev/null
+++ b/params_shard_43.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be253b2a24a5ba06c2747d4f5d52654813f69d39f659a015f1b96476e42a7c61
+size 32063488
diff --git a/params_shard_44.bin b/params_shard_44.bin
new file mode 100644
index 0000000000000000000000000000000000000000..9bf1eadd8567b93a7fadac7dda3fa2af164d774c
--- /dev/null
+++ b/params_shard_44.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9f8f981bb2d3092f10939c6c8a423ef3b0999d4f90f3c5454287b8a9c83658
+size 45088768
diff --git a/params_shard_45.bin b/params_shard_45.bin
new file mode 100644
index 0000000000000000000000000000000000000000..06b91e790e2a1e60659af69c9da9144002c5f256
--- /dev/null
+++ b/params_shard_45.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732d2046d33c7e3a2c7b71f3a20d6ba42a9e1b3aab8d1d7e8d4e819bbb630f8f
+size 22544384
diff --git a/params_shard_46.bin b/params_shard_46.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1f8a0d346427ff1f7c5440325363d985ff15e049
--- /dev/null
+++ b/params_shard_46.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81db2b2bc6460cce9dc7b62506d9506bc9ba0de0bb59679b6aaeae277a9f3b04
+size 25165824
diff --git a/params_shard_47.bin b/params_shard_47.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e4f80abe7ac5664780f238300bcd4fdfe40c66f6
--- /dev/null
+++ b/params_shard_47.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3f2f56d0cf44fa859c770a32e585c7a239ac65b61d753c8a465029ec308867
+size 32587776
diff --git a/params_shard_48.bin b/params_shard_48.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e3a61a6893c9128b2dc647b5497069167b988a52
--- /dev/null
+++ b/params_shard_48.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee514a6d9da0a4227eb4dc467229e2ca5359b692515de925927add7359326be
+size 45088768
diff --git a/params_shard_49.bin b/params_shard_49.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7bb7f541e18b083a089ec2a2f93fe48f370ef07e
--- /dev/null
+++ b/params_shard_49.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37dc55b4b1062f0d8226218394bdb3912a4daea21167dcd16528f44097146ea5
+size 25165824
diff --git a/params_shard_5.bin b/params_shard_5.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6ed8cc18b7b72370e9d3104bee2a67bf945df7b
--- /dev/null
+++ b/params_shard_5.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ef0ebc699ec302c69c86d3f5eadcc43bc4057ed8ed5cc501d5664292a7de45
+size 32587776
diff --git a/params_shard_50.bin b/params_shard_50.bin
new file mode 100644
index 0000000000000000000000000000000000000000..198dd7a943ed0c77753426b0ba3251d6cd2a0b06
--- /dev/null
+++ b/params_shard_50.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d73e6b993ab7f5f94cc682fe19500fbd2ecd383183cbd57d4a37f270d0121d7
+size 32063488
diff --git a/params_shard_51.bin b/params_shard_51.bin
new file mode 100644
index 0000000000000000000000000000000000000000..35379565388d6a6e5e7991ed516864d1703972e2
--- /dev/null
+++ b/params_shard_51.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436c9a71165dd110ba56de263ae158a4b77eb9261fa4221f997115364e77f7de
+size 45088768
diff --git a/params_shard_52.bin b/params_shard_52.bin
new file mode 100644
index 0000000000000000000000000000000000000000..461e35aa4083d2ad28fa406b3cdfd953df8c90bd
--- /dev/null
+++ b/params_shard_52.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2b910b28688f194761076b166da54cb1c527ed8fdf4d6dcb2dc3df6a9d9b0a
+size 22544384
diff --git a/params_shard_53.bin b/params_shard_53.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b936a2575328e069bb9d514b3533221046b925de
--- /dev/null
+++ b/params_shard_53.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065c959c40aa3612f4549768cab3cd8ad04e4c8ec2af1c7992739621feb1f213
+size 25165824
diff --git a/params_shard_54.bin b/params_shard_54.bin
new file mode 100644
index 0000000000000000000000000000000000000000..69f0372d565f5187723aa7a136e2f6db7f0a0274
--- /dev/null
+++ b/params_shard_54.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd9aad6c54f5f6165e4875129269281cb709e8c926caf7010e03c7d97f66a46
+size 32587776
diff --git a/params_shard_55.bin b/params_shard_55.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dd1890de8cad8b5ee673a64d5b297ecd4d93116d
--- /dev/null
+++ b/params_shard_55.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b4794615cec9242a2e7268cc3b84ecb3ce8e912b7cf855530b8f0ceef19588
+size 45088768
diff --git a/params_shard_56.bin b/params_shard_56.bin
new file mode 100644
index 0000000000000000000000000000000000000000..891fda03bac282d352a0f9ffc239f69a093f1e5a
--- /dev/null
+++ b/params_shard_56.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a431b5a392f406b28090790dd856854bce144e0b66b188f42ad7c451535dc6
+size 25165824
diff --git a/params_shard_57.bin b/params_shard_57.bin
new file mode 100644
index 0000000000000000000000000000000000000000..70da943fa5ef99cce48d0d4091ee1a8141363f76
--- /dev/null
+++ b/params_shard_57.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ee4626ed0915ab15fcde422f3ffb77f7424cadea08dac3a0d4b85189b1386b
+size 32063488
diff --git a/params_shard_58.bin b/params_shard_58.bin
new file mode 100644
index 0000000000000000000000000000000000000000..82bca98a3cd32a236badf13139bcc91aa2d5bcc0
--- /dev/null
+++ b/params_shard_58.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c883fc3ec1c600b29afffda9ea4f6e07aba55d86a391fca283027ac10ab9177c
+size 45088768
diff --git a/params_shard_59.bin b/params_shard_59.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b3cd97ce66c892bc00e2ed11313c307dd0cb88b1
--- /dev/null
+++ b/params_shard_59.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e2f916be842d6c524e7ea30230e0d253537c9c679e633ea45285c70ca78b6f
+size 22544384
diff --git a/params_shard_6.bin b/params_shard_6.bin
new file mode 100644
index 0000000000000000000000000000000000000000..52d34234c2d607bb2df33e85ce06732923d7ba35
--- /dev/null
+++ b/params_shard_6.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ffd84972c16bbc806beab6d1b59ae9311fbc979f98b567b4e56c2b35bf0381
+size 45088768
diff --git a/params_shard_60.bin b/params_shard_60.bin
new file mode 100644
index 0000000000000000000000000000000000000000..361c20551688bbd3b7af9f9615855aed4a3fb284
--- /dev/null
+++ b/params_shard_60.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d019aa1aed0d486c765aa6b29e38522961657c8f4c250680241fe4eebf74673
+size 25165824
diff --git a/params_shard_61.bin b/params_shard_61.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0192f9410a2e21ad6714e744b6206e38af06f9e1
--- /dev/null
+++ b/params_shard_61.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c872c5679061cc510e581fdcee9260b13e79edd54fe08035a7f105881ee84abf
+size 32587776
diff --git a/params_shard_62.bin b/params_shard_62.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3adc3c7c4469cbc725b69e41c1a31898f8edbb1b
--- /dev/null
+++ b/params_shard_62.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9b3e8df197059b70d3628b1ebed9adfdbde391b80ed6056904406919286318
+size 45088768
diff --git a/params_shard_63.bin b/params_shard_63.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5875f7949bf9b1e39391e19d9dfabe0655eaee26
--- /dev/null
+++ b/params_shard_63.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360905fd80989e0c86f8279b7f5f6b0a90f54b8565696146e94d71be4154ffb5
+size 25165824
diff --git a/params_shard_64.bin b/params_shard_64.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ec92c4820884c4ac9f983ad31f881e6f194eda95
--- /dev/null
+++ b/params_shard_64.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d039fdf4f4955ed7ff52d429e9ac0ac10cad1094421ad59aa7f80f81aed5b7c
+size 32063488
diff --git a/params_shard_65.bin b/params_shard_65.bin
new file mode 100644
index 0000000000000000000000000000000000000000..43c449ebfb8e6596ffc79eaaf8c83ba16484f6b6
--- /dev/null
+++ b/params_shard_65.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a164423f0e571c2958dc3748225d3c8deaf60e80b4c10f374978da9e4713d710
+size 45088768
diff --git a/params_shard_66.bin b/params_shard_66.bin
new file mode 100644
index 0000000000000000000000000000000000000000..303404d0d72de6a061f32311df8c22f86154d966
--- /dev/null
+++ b/params_shard_66.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b14128381a830f4099c44c0bd20c6acd81f543d9ffb9ea18332eff2c746207
+size 22544384
diff --git a/params_shard_67.bin b/params_shard_67.bin
new file mode 100644
index 0000000000000000000000000000000000000000..a0ae0f75d5d37f2c145a64ef0251a43bba5946df
--- /dev/null
+++ b/params_shard_67.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4458f60269d771cbe941ea2a26952bfc7d24e611d64ee320b22571eecd88ad32
+size 25165824
diff --git a/params_shard_68.bin b/params_shard_68.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8835eb099ab6707f4c3b856c7c8dde4967726d23
--- /dev/null
+++ b/params_shard_68.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8304eff737e201d73b2439d7d05f27a81dd279bbb5b61b7a2d4c28d617e9082e
+size 32587776
diff --git a/params_shard_69.bin b/params_shard_69.bin
new file mode 100644
index 0000000000000000000000000000000000000000..345e606d47b8114cb9311e74ae1ab8a18249f457
--- /dev/null
+++ b/params_shard_69.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a5fc7608d1ef87745a17be6ba8b255a1f89d3403925b55732fdbc0666bbe96
+size 45088768
diff --git a/params_shard_7.bin b/params_shard_7.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dcb49175ea7feed19c7c0ad05c14d432a5e9e039
--- /dev/null
+++ b/params_shard_7.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94b7a68e7e505d377c861f2ca9890f54fbdafc43f8c11f9ebd5e8ddc6e4a404
+size 25165824
diff --git a/params_shard_70.bin b/params_shard_70.bin
new file mode 100644
index 0000000000000000000000000000000000000000..48785eeb04aae046bd85bd3ea78be9f9e76c9d82
--- /dev/null
+++ b/params_shard_70.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8b3a4f84051090149f085e1194838007724092391efbb8abb7abf4c443823c
+size 25165824
diff --git a/params_shard_71.bin b/params_shard_71.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0158a082b5a0762d9bb0556083ea767c2a2f9c74
--- /dev/null
+++ b/params_shard_71.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58260331159d9bcc585390a7eaea34344f88e74019856a9fc4752519f4f21190
+size 32063488
diff --git a/params_shard_72.bin b/params_shard_72.bin
new file mode 100644
index 0000000000000000000000000000000000000000..dcddd5cff3ea5df31778a23f751f755c8fcb424a
--- /dev/null
+++ b/params_shard_72.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945ef7b7a14ae6aef8e13c7be08cb92bcd7347a59c43aa23dc3f5ec706a7a730
+size 45088768
diff --git a/params_shard_73.bin b/params_shard_73.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7e204f4e5b4baf8552e7cda64af73b4a121f216c
--- /dev/null
+++ b/params_shard_73.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5380c6cbf738679f6a75e8cf4cce3c316e2fa30c88ac00a0e4409bda002679a9
+size 22544384
diff --git a/params_shard_74.bin b/params_shard_74.bin
new file mode 100644
index 0000000000000000000000000000000000000000..39ca72dfa9ab9a20e2a7852b843e79f8aa386b11
--- /dev/null
+++ b/params_shard_74.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3efbb5f7c4393f08ef5886ce310e995c0a6a4de9eec1a6797f1dea70e17201
+size 25165824
diff --git a/params_shard_75.bin b/params_shard_75.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b082500e0b472d3de51f136a919f4155ac2e7134
--- /dev/null
+++ b/params_shard_75.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff087ae7715b697e9abd11f602d9af1fef1d37562eabb2db320c88356bcb867
+size 32587776
diff --git a/params_shard_76.bin b/params_shard_76.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8acc807af80db4d05af439859f0e31316fe89f34
--- /dev/null
+++ b/params_shard_76.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbaed22171ac0e77a34d4b1d4456556c28be7aa43eb97b03391dd519456be17
+size 45088768
diff --git a/params_shard_77.bin b/params_shard_77.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ab7d26bc19f3ce625841e72d71aa84966e49441a
--- /dev/null
+++ b/params_shard_77.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b516280ba7a808012287a184f78add18e4babdc83fbe4c89112ab1683a1a06
+size 25165824
diff --git a/params_shard_78.bin b/params_shard_78.bin
new file mode 100644
index 0000000000000000000000000000000000000000..68ed8df8e64b2c01d0e3fcdec569631fdf5793cb
--- /dev/null
+++ b/params_shard_78.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54ba0494a67b2d098ecbf73597bb34e07c540befc72dfeb661baece2c629ba3
+size 32063488
diff --git a/params_shard_79.bin b/params_shard_79.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bf5c8a6dccb3b2d0e8c326b4ae3a6b73499297cd
--- /dev/null
+++ b/params_shard_79.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedf11f77813daf0232965a60d41be30c9bbf4ab1f484403488617f4d81c1897
+size 45088768
diff --git a/params_shard_8.bin b/params_shard_8.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b682bbe428d400e5b138e51a01063f2da00acbea
--- /dev/null
+++ b/params_shard_8.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1bd042c87865782350b6040fed620f5430c76a88df374a6677814a9a516cf34
+size 32063488
diff --git a/params_shard_80.bin b/params_shard_80.bin
new file mode 100644
index 0000000000000000000000000000000000000000..02728761db46535bd0bf2800ec46d0bbb2331a98
--- /dev/null
+++ b/params_shard_80.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55fcee003ae7f7e19b31633479215f9102d77bc3e0d9c91b6b20b9eeb25df911
+size 22544384
diff --git a/params_shard_81.bin b/params_shard_81.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3c5cd241cdada918688de1a40ce278fd3001b3d1
--- /dev/null
+++ b/params_shard_81.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ba360c458060ea1961676f16412fefdd6794bcbf7eda12aab7460fd653ce62
+size 25165824
diff --git a/params_shard_82.bin b/params_shard_82.bin
new file mode 100644
index 0000000000000000000000000000000000000000..37fe15eb6901cbc81ad8c4bd6569053358e4918b
--- /dev/null
+++ b/params_shard_82.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ccf90f47dc5a9efc0a0adc8342a992baf0e9be4e1ee0ddb213e50bee9d5ec4
+size 32587776
diff --git a/params_shard_83.bin b/params_shard_83.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0edc560a111db1426cba7f76c459e73d59608352
--- /dev/null
+++ b/params_shard_83.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1a43ea1a97ca97c46bcf628c4f37089a0ddb16da87eadbcfeefc11070e494d
+size 45088768
diff --git a/params_shard_84.bin b/params_shard_84.bin
new file mode 100644
index 0000000000000000000000000000000000000000..63de84b87fed4e80021a01d75945e573aeec8e51
--- /dev/null
+++ b/params_shard_84.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b60c9db9c1ebdab3ccc72604dcc7b7fe5daf53e7945cebe6c5a653a073a272
+size 25165824
diff --git a/params_shard_85.bin b/params_shard_85.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4e84b53799f285049a462a82b90218685809234d
--- /dev/null
+++ b/params_shard_85.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa526c5277ee17be94d7159feac97de8d9bfa6ca67d2dda4f3c964a03d6a8d1
+size 32063488
diff --git a/params_shard_86.bin b/params_shard_86.bin
new file mode 100644
index 0000000000000000000000000000000000000000..db3afefc932fc2879856eea232c30ace0cfb3e3d
--- /dev/null
+++ b/params_shard_86.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300abd62b54ab838e93220e3d03480d1ca5a9fbd48457c39f65f3effe0302ff7
+size 45088768
diff --git a/params_shard_87.bin b/params_shard_87.bin
new file mode 100644
index 0000000000000000000000000000000000000000..e6c50afd72278ecfd6e75d672240fb9635a42150
--- /dev/null
+++ b/params_shard_87.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4041bf3356ecefebae90cba5fc0b96459cf9fb22dac6df3a4f0492de5a5513c1
+size 22544384
diff --git a/params_shard_88.bin b/params_shard_88.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eaee7f8db5791321427e29a66c3d29df183e80b0
--- /dev/null
+++ b/params_shard_88.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d51d1771e012111e033282bdd190e444b7325344c29a4b5edf2121e5001d33
+size 25165824
diff --git a/params_shard_89.bin b/params_shard_89.bin
new file mode 100644
index 0000000000000000000000000000000000000000..bf27cf935943e4575f46cf6ad006ea8d9dd29202
--- /dev/null
+++ b/params_shard_89.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f2993d5391e06082c56ff398c9817c954dbdbffd2466aa256c14758206a646
+size 32587776
diff --git a/params_shard_9.bin b/params_shard_9.bin
new file mode 100644
index 0000000000000000000000000000000000000000..16dcf53bf154a2101d9c68dc8f043bd0250cd28d
--- /dev/null
+++ b/params_shard_9.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9142a26f6f3caf2a240a4756c92e06bfbff8357b984bf1058f29e1ba3f099bcd
+size 45088768
diff --git a/params_shard_90.bin b/params_shard_90.bin
new file mode 100644
index 0000000000000000000000000000000000000000..56b812a3496dfdee130cf0201d655faa1b8cc9d8
--- /dev/null
+++ b/params_shard_90.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b60b0c9ce8c390408d7dd48c2a913fb93eb00f346dbfcf76c44a8356ca4ee3
+size 45088768
diff --git a/params_shard_91.bin b/params_shard_91.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ff10145c37b29b4e888d85645b26bae57b16f6b6
--- /dev/null
+++ b/params_shard_91.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcbc8d5382eb1474cca891fdfdb95e951b00a0abad0f19e4896309c63deef1b
+size 25165824
diff --git a/params_shard_92.bin b/params_shard_92.bin
new file mode 100644
index 0000000000000000000000000000000000000000..16838831dc8125de1962404cfa45d62a1c14c969
--- /dev/null
+++ b/params_shard_92.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587fe90491ef639ac84bca23db08ca3ec24459a8ca2ae2a79ab2141188b79feb
+size 32063488
diff --git a/params_shard_93.bin b/params_shard_93.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d748795da53ed13eaabba162e7dd3e4838fcfdaf
--- /dev/null
+++ b/params_shard_93.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937fdd3b45753fe8243479632f09b416fdfbf1e60dd4bd1386a2ad216f13aab5
+size 45088768
diff --git a/params_shard_94.bin b/params_shard_94.bin
new file mode 100644
index 0000000000000000000000000000000000000000..eefd56e313020d029998bde305186eb11f9df6f3
--- /dev/null
+++ b/params_shard_94.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba94e6de585eb60dd5a2b16423805494de6dd2c8f14c0c05800ed29f867f4344
+size 22544384
diff --git a/params_shard_95.bin b/params_shard_95.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f2befe2bfa87ca3ff33116ded61fa65f3eab1e4c
--- /dev/null
+++ b/params_shard_95.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf94e0a70af2def020ce2263fb146b0dbc78eca1fbd962a1a51df883023781
+size 25165824
diff --git a/params_shard_96.bin b/params_shard_96.bin
new file mode 100644
index 0000000000000000000000000000000000000000..010987be09a0ef5285810fa77657670c4d272ca9
--- /dev/null
+++ b/params_shard_96.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137a1660c4d95f74063864e3441f6277103ea2626f09a80e2dc861947cfad3b4
+size 32587776
diff --git a/params_shard_97.bin b/params_shard_97.bin
new file mode 100644
index 0000000000000000000000000000000000000000..2209654dedf8bf2d203185d8b7209284909c3e6a
--- /dev/null
+++ b/params_shard_97.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa47f32437012f42af829db394791ee7a1c8a536d4dcba35cd7e01e7f8c3f1c2
+size 45088768
diff --git a/params_shard_98.bin b/params_shard_98.bin
new file mode 100644
index 0000000000000000000000000000000000000000..21d05137bfd06247261cb1c81b4054144082561e
--- /dev/null
+++ b/params_shard_98.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ba4ef3e96cd35eb4c4fe09f69ac283419bc6392aea4776535a10692b066e06
+size 25165824
diff --git a/params_shard_99.bin b/params_shard_99.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ecd8f4989c37ac3a983257895370fd2c0a07d070
--- /dev/null
+++ b/params_shard_99.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66461f5e730cb629cdf9fb3b5253b73a43d2abfbe55242d6ffb2ebc1507b51c
+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..5ab645d5171518423ba4c2f6503c5c22e5d0a3ed
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,34 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "model_max_length": 2048,
+ "pad_token": null,
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}