iyanello commited on
Commit
74a7a48
1 Parent(s): 6397d59

Upload 52 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ TinyLlama-1.1B-Chat-v1.0-q8f16_1-metal_x86_64.dylib filter=lfs diff=lfs merge=lfs -text
TinyLlama-1.1B-Chat-v1.0-q8f16_1-metal_x86_64.dylib ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6868d637572a461453a3d6973cb7b152bad82b32740b8ff1d635abc94d7b7f2
3
+ size 2145120
mlc-chat-config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_lib": "TinyLlama-1.1B-Chat-v1.0-q8f16_1",
3
+ "local_id": "TinyLlama-1.1B-Chat-v1.0-q8f16_1",
4
+ "conv_template": "chatml",
5
+ "temperature": 0.7,
6
+ "repetition_penalty": 1.0,
7
+ "top_p": 0.95,
8
+ "mean_gen_len": 128,
9
+ "max_gen_len": 2048,
10
+ "num_shards": 1,
11
+ "use_presharded_weights": false,
12
+ "shift_fill_factor": 0.3,
13
+ "tokenizer_files": [
14
+ "tokenizer.json",
15
+ "tokenizer.model"
16
+ ],
17
+ "model_category": "llama",
18
+ "model_name": "TinyLlama-1.1B-Chat-v1.0",
19
+ "vocab_size": 32000,
20
+ "prefill_chunk_size": -1,
21
+ "max_window_size": 2048
22
+ }
ndarray-cache.json ADDED
@@ -0,0 +1,2827 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "ParamSize": 227
4
+ },
5
+ "records": [
6
+ {
7
+ "dataPath": "params_shard_0.bin",
8
+ "format": "raw-shard",
9
+ "nbytes": 65536000,
10
+ "records": [
11
+ {
12
+ "name": "param_0",
13
+ "shape": [
14
+ 32000,
15
+ 512
16
+ ],
17
+ "dtype": "uint32",
18
+ "format": "raw",
19
+ "nbytes": 65536000,
20
+ "byteOffset": 0
21
+ }
22
+ ],
23
+ "md5sum": "f07a020ee2f5daeff501f56ea505adec"
24
+ },
25
+ {
26
+ "dataPath": "params_shard_1.bin",
27
+ "format": "raw-shard",
28
+ "nbytes": 23068672,
29
+ "records": [
30
+ {
31
+ "name": "param_6",
32
+ "shape": [
33
+ 11264,
34
+ 512
35
+ ],
36
+ "dtype": "uint32",
37
+ "format": "raw",
38
+ "nbytes": 23068672,
39
+ "byteOffset": 0
40
+ }
41
+ ],
42
+ "md5sum": "63e11b3f33abf74b904888093dfdfa24"
43
+ },
44
+ {
45
+ "dataPath": "params_shard_2.bin",
46
+ "format": "raw-shard",
47
+ "nbytes": 33398784,
48
+ "records": [
49
+ {
50
+ "name": "param_1",
51
+ "shape": [
52
+ 32000,
53
+ 64
54
+ ],
55
+ "dtype": "float16",
56
+ "format": "raw",
57
+ "nbytes": 4096000,
58
+ "byteOffset": 0
59
+ },
60
+ {
61
+ "name": "param_2",
62
+ "shape": [
63
+ 2560,
64
+ 512
65
+ ],
66
+ "dtype": "uint32",
67
+ "format": "raw",
68
+ "nbytes": 5242880,
69
+ "byteOffset": 4096000
70
+ },
71
+ {
72
+ "name": "param_3",
73
+ "shape": [
74
+ 2560,
75
+ 64
76
+ ],
77
+ "dtype": "float16",
78
+ "format": "raw",
79
+ "nbytes": 327680,
80
+ "byteOffset": 9338880
81
+ },
82
+ {
83
+ "name": "param_4",
84
+ "shape": [
85
+ 2048,
86
+ 512
87
+ ],
88
+ "dtype": "uint32",
89
+ "format": "raw",
90
+ "nbytes": 4194304,
91
+ "byteOffset": 9666560
92
+ },
93
+ {
94
+ "name": "param_5",
95
+ "shape": [
96
+ 2048,
97
+ 64
98
+ ],
99
+ "dtype": "float16",
100
+ "format": "raw",
101
+ "nbytes": 262144,
102
+ "byteOffset": 13860864
103
+ },
104
+ {
105
+ "name": "param_7",
106
+ "shape": [
107
+ 11264,
108
+ 64
109
+ ],
110
+ "dtype": "float16",
111
+ "format": "raw",
112
+ "nbytes": 1441792,
113
+ "byteOffset": 14123008
114
+ },
115
+ {
116
+ "name": "param_8",
117
+ "shape": [
118
+ 2048,
119
+ 1408
120
+ ],
121
+ "dtype": "uint32",
122
+ "format": "raw",
123
+ "nbytes": 11534336,
124
+ "byteOffset": 15564800
125
+ },
126
+ {
127
+ "name": "param_9",
128
+ "shape": [
129
+ 2048,
130
+ 176
131
+ ],
132
+ "dtype": "float16",
133
+ "format": "raw",
134
+ "nbytes": 720896,
135
+ "byteOffset": 27099136
136
+ },
137
+ {
138
+ "name": "param_10",
139
+ "shape": [
140
+ 2048
141
+ ],
142
+ "dtype": "float16",
143
+ "format": "raw",
144
+ "nbytes": 4096,
145
+ "byteOffset": 27820032
146
+ },
147
+ {
148
+ "name": "param_11",
149
+ "shape": [
150
+ 2048
151
+ ],
152
+ "dtype": "float16",
153
+ "format": "raw",
154
+ "nbytes": 4096,
155
+ "byteOffset": 27824128
156
+ },
157
+ {
158
+ "name": "param_12",
159
+ "shape": [
160
+ 2560,
161
+ 512
162
+ ],
163
+ "dtype": "uint32",
164
+ "format": "raw",
165
+ "nbytes": 5242880,
166
+ "byteOffset": 27828224
167
+ },
168
+ {
169
+ "name": "param_13",
170
+ "shape": [
171
+ 2560,
172
+ 64
173
+ ],
174
+ "dtype": "float16",
175
+ "format": "raw",
176
+ "nbytes": 327680,
177
+ "byteOffset": 33071104
178
+ }
179
+ ],
180
+ "md5sum": "9185bca177317d270f55d36199df1f3d"
181
+ },
182
+ {
183
+ "dataPath": "params_shard_3.bin",
184
+ "format": "raw-shard",
185
+ "nbytes": 28966912,
186
+ "records": [
187
+ {
188
+ "name": "param_14",
189
+ "shape": [
190
+ 2048,
191
+ 512
192
+ ],
193
+ "dtype": "uint32",
194
+ "format": "raw",
195
+ "nbytes": 4194304,
196
+ "byteOffset": 0
197
+ },
198
+ {
199
+ "name": "param_15",
200
+ "shape": [
201
+ 2048,
202
+ 64
203
+ ],
204
+ "dtype": "float16",
205
+ "format": "raw",
206
+ "nbytes": 262144,
207
+ "byteOffset": 4194304
208
+ },
209
+ {
210
+ "name": "param_16",
211
+ "shape": [
212
+ 11264,
213
+ 512
214
+ ],
215
+ "dtype": "uint32",
216
+ "format": "raw",
217
+ "nbytes": 23068672,
218
+ "byteOffset": 4456448
219
+ },
220
+ {
221
+ "name": "param_17",
222
+ "shape": [
223
+ 11264,
224
+ 64
225
+ ],
226
+ "dtype": "float16",
227
+ "format": "raw",
228
+ "nbytes": 1441792,
229
+ "byteOffset": 27525120
230
+ }
231
+ ],
232
+ "md5sum": "2da6dc4ff9de3d49eb4035d908635a3d"
233
+ },
234
+ {
235
+ "dataPath": "params_shard_4.bin",
236
+ "format": "raw-shard",
237
+ "nbytes": 23068672,
238
+ "records": [
239
+ {
240
+ "name": "param_26",
241
+ "shape": [
242
+ 11264,
243
+ 512
244
+ ],
245
+ "dtype": "uint32",
246
+ "format": "raw",
247
+ "nbytes": 23068672,
248
+ "byteOffset": 0
249
+ }
250
+ ],
251
+ "md5sum": "38dae57488e45c49c9eb6588b08ca08f"
252
+ },
253
+ {
254
+ "dataPath": "params_shard_5.bin",
255
+ "format": "raw-shard",
256
+ "nbytes": 23732224,
257
+ "records": [
258
+ {
259
+ "name": "param_18",
260
+ "shape": [
261
+ 2048,
262
+ 1408
263
+ ],
264
+ "dtype": "uint32",
265
+ "format": "raw",
266
+ "nbytes": 11534336,
267
+ "byteOffset": 0
268
+ },
269
+ {
270
+ "name": "param_19",
271
+ "shape": [
272
+ 2048,
273
+ 176
274
+ ],
275
+ "dtype": "float16",
276
+ "format": "raw",
277
+ "nbytes": 720896,
278
+ "byteOffset": 11534336
279
+ },
280
+ {
281
+ "name": "param_20",
282
+ "shape": [
283
+ 2048
284
+ ],
285
+ "dtype": "float16",
286
+ "format": "raw",
287
+ "nbytes": 4096,
288
+ "byteOffset": 12255232
289
+ },
290
+ {
291
+ "name": "param_21",
292
+ "shape": [
293
+ 2048
294
+ ],
295
+ "dtype": "float16",
296
+ "format": "raw",
297
+ "nbytes": 4096,
298
+ "byteOffset": 12259328
299
+ },
300
+ {
301
+ "name": "param_22",
302
+ "shape": [
303
+ 2560,
304
+ 512
305
+ ],
306
+ "dtype": "uint32",
307
+ "format": "raw",
308
+ "nbytes": 5242880,
309
+ "byteOffset": 12263424
310
+ },
311
+ {
312
+ "name": "param_23",
313
+ "shape": [
314
+ 2560,
315
+ 64
316
+ ],
317
+ "dtype": "float16",
318
+ "format": "raw",
319
+ "nbytes": 327680,
320
+ "byteOffset": 17506304
321
+ },
322
+ {
323
+ "name": "param_24",
324
+ "shape": [
325
+ 2048,
326
+ 512
327
+ ],
328
+ "dtype": "uint32",
329
+ "format": "raw",
330
+ "nbytes": 4194304,
331
+ "byteOffset": 17833984
332
+ },
333
+ {
334
+ "name": "param_25",
335
+ "shape": [
336
+ 2048,
337
+ 64
338
+ ],
339
+ "dtype": "float16",
340
+ "format": "raw",
341
+ "nbytes": 262144,
342
+ "byteOffset": 22028288
343
+ },
344
+ {
345
+ "name": "param_27",
346
+ "shape": [
347
+ 11264,
348
+ 64
349
+ ],
350
+ "dtype": "float16",
351
+ "format": "raw",
352
+ "nbytes": 1441792,
353
+ "byteOffset": 22290432
354
+ }
355
+ ],
356
+ "md5sum": "027b9b7ffbf218216c89cd3597b6f9c4"
357
+ },
358
+ {
359
+ "dataPath": "params_shard_6.bin",
360
+ "format": "raw-shard",
361
+ "nbytes": 23068672,
362
+ "records": [
363
+ {
364
+ "name": "param_36",
365
+ "shape": [
366
+ 11264,
367
+ 512
368
+ ],
369
+ "dtype": "uint32",
370
+ "format": "raw",
371
+ "nbytes": 23068672,
372
+ "byteOffset": 0
373
+ }
374
+ ],
375
+ "md5sum": "73fd6b56c6349030bbeba1aefdd0b6d5"
376
+ },
377
+ {
378
+ "dataPath": "params_shard_7.bin",
379
+ "format": "raw-shard",
380
+ "nbytes": 23732224,
381
+ "records": [
382
+ {
383
+ "name": "param_28",
384
+ "shape": [
385
+ 2048,
386
+ 1408
387
+ ],
388
+ "dtype": "uint32",
389
+ "format": "raw",
390
+ "nbytes": 11534336,
391
+ "byteOffset": 0
392
+ },
393
+ {
394
+ "name": "param_29",
395
+ "shape": [
396
+ 2048,
397
+ 176
398
+ ],
399
+ "dtype": "float16",
400
+ "format": "raw",
401
+ "nbytes": 720896,
402
+ "byteOffset": 11534336
403
+ },
404
+ {
405
+ "name": "param_30",
406
+ "shape": [
407
+ 2048
408
+ ],
409
+ "dtype": "float16",
410
+ "format": "raw",
411
+ "nbytes": 4096,
412
+ "byteOffset": 12255232
413
+ },
414
+ {
415
+ "name": "param_31",
416
+ "shape": [
417
+ 2048
418
+ ],
419
+ "dtype": "float16",
420
+ "format": "raw",
421
+ "nbytes": 4096,
422
+ "byteOffset": 12259328
423
+ },
424
+ {
425
+ "name": "param_32",
426
+ "shape": [
427
+ 2560,
428
+ 512
429
+ ],
430
+ "dtype": "uint32",
431
+ "format": "raw",
432
+ "nbytes": 5242880,
433
+ "byteOffset": 12263424
434
+ },
435
+ {
436
+ "name": "param_33",
437
+ "shape": [
438
+ 2560,
439
+ 64
440
+ ],
441
+ "dtype": "float16",
442
+ "format": "raw",
443
+ "nbytes": 327680,
444
+ "byteOffset": 17506304
445
+ },
446
+ {
447
+ "name": "param_34",
448
+ "shape": [
449
+ 2048,
450
+ 512
451
+ ],
452
+ "dtype": "uint32",
453
+ "format": "raw",
454
+ "nbytes": 4194304,
455
+ "byteOffset": 17833984
456
+ },
457
+ {
458
+ "name": "param_35",
459
+ "shape": [
460
+ 2048,
461
+ 64
462
+ ],
463
+ "dtype": "float16",
464
+ "format": "raw",
465
+ "nbytes": 262144,
466
+ "byteOffset": 22028288
467
+ },
468
+ {
469
+ "name": "param_37",
470
+ "shape": [
471
+ 11264,
472
+ 64
473
+ ],
474
+ "dtype": "float16",
475
+ "format": "raw",
476
+ "nbytes": 1441792,
477
+ "byteOffset": 22290432
478
+ }
479
+ ],
480
+ "md5sum": "4e0d4e392e16dfb010e112a552db6611"
481
+ },
482
+ {
483
+ "dataPath": "params_shard_8.bin",
484
+ "format": "raw-shard",
485
+ "nbytes": 23068672,
486
+ "records": [
487
+ {
488
+ "name": "param_46",
489
+ "shape": [
490
+ 11264,
491
+ 512
492
+ ],
493
+ "dtype": "uint32",
494
+ "format": "raw",
495
+ "nbytes": 23068672,
496
+ "byteOffset": 0
497
+ }
498
+ ],
499
+ "md5sum": "6f2ddaf5768b5e2a1fcb8e6608dfb7d9"
500
+ },
501
+ {
502
+ "dataPath": "params_shard_9.bin",
503
+ "format": "raw-shard",
504
+ "nbytes": 23732224,
505
+ "records": [
506
+ {
507
+ "name": "param_38",
508
+ "shape": [
509
+ 2048,
510
+ 1408
511
+ ],
512
+ "dtype": "uint32",
513
+ "format": "raw",
514
+ "nbytes": 11534336,
515
+ "byteOffset": 0
516
+ },
517
+ {
518
+ "name": "param_39",
519
+ "shape": [
520
+ 2048,
521
+ 176
522
+ ],
523
+ "dtype": "float16",
524
+ "format": "raw",
525
+ "nbytes": 720896,
526
+ "byteOffset": 11534336
527
+ },
528
+ {
529
+ "name": "param_40",
530
+ "shape": [
531
+ 2048
532
+ ],
533
+ "dtype": "float16",
534
+ "format": "raw",
535
+ "nbytes": 4096,
536
+ "byteOffset": 12255232
537
+ },
538
+ {
539
+ "name": "param_41",
540
+ "shape": [
541
+ 2048
542
+ ],
543
+ "dtype": "float16",
544
+ "format": "raw",
545
+ "nbytes": 4096,
546
+ "byteOffset": 12259328
547
+ },
548
+ {
549
+ "name": "param_42",
550
+ "shape": [
551
+ 2560,
552
+ 512
553
+ ],
554
+ "dtype": "uint32",
555
+ "format": "raw",
556
+ "nbytes": 5242880,
557
+ "byteOffset": 12263424
558
+ },
559
+ {
560
+ "name": "param_43",
561
+ "shape": [
562
+ 2560,
563
+ 64
564
+ ],
565
+ "dtype": "float16",
566
+ "format": "raw",
567
+ "nbytes": 327680,
568
+ "byteOffset": 17506304
569
+ },
570
+ {
571
+ "name": "param_44",
572
+ "shape": [
573
+ 2048,
574
+ 512
575
+ ],
576
+ "dtype": "uint32",
577
+ "format": "raw",
578
+ "nbytes": 4194304,
579
+ "byteOffset": 17833984
580
+ },
581
+ {
582
+ "name": "param_45",
583
+ "shape": [
584
+ 2048,
585
+ 64
586
+ ],
587
+ "dtype": "float16",
588
+ "format": "raw",
589
+ "nbytes": 262144,
590
+ "byteOffset": 22028288
591
+ },
592
+ {
593
+ "name": "param_47",
594
+ "shape": [
595
+ 11264,
596
+ 64
597
+ ],
598
+ "dtype": "float16",
599
+ "format": "raw",
600
+ "nbytes": 1441792,
601
+ "byteOffset": 22290432
602
+ }
603
+ ],
604
+ "md5sum": "196aa0c86be56458981f79fd8e56439b"
605
+ },
606
+ {
607
+ "dataPath": "params_shard_10.bin",
608
+ "format": "raw-shard",
609
+ "nbytes": 23068672,
610
+ "records": [
611
+ {
612
+ "name": "param_56",
613
+ "shape": [
614
+ 11264,
615
+ 512
616
+ ],
617
+ "dtype": "uint32",
618
+ "format": "raw",
619
+ "nbytes": 23068672,
620
+ "byteOffset": 0
621
+ }
622
+ ],
623
+ "md5sum": "546eda8f4da59ad911790082967eb065"
624
+ },
625
+ {
626
+ "dataPath": "params_shard_11.bin",
627
+ "format": "raw-shard",
628
+ "nbytes": 23732224,
629
+ "records": [
630
+ {
631
+ "name": "param_48",
632
+ "shape": [
633
+ 2048,
634
+ 1408
635
+ ],
636
+ "dtype": "uint32",
637
+ "format": "raw",
638
+ "nbytes": 11534336,
639
+ "byteOffset": 0
640
+ },
641
+ {
642
+ "name": "param_49",
643
+ "shape": [
644
+ 2048,
645
+ 176
646
+ ],
647
+ "dtype": "float16",
648
+ "format": "raw",
649
+ "nbytes": 720896,
650
+ "byteOffset": 11534336
651
+ },
652
+ {
653
+ "name": "param_50",
654
+ "shape": [
655
+ 2048
656
+ ],
657
+ "dtype": "float16",
658
+ "format": "raw",
659
+ "nbytes": 4096,
660
+ "byteOffset": 12255232
661
+ },
662
+ {
663
+ "name": "param_51",
664
+ "shape": [
665
+ 2048
666
+ ],
667
+ "dtype": "float16",
668
+ "format": "raw",
669
+ "nbytes": 4096,
670
+ "byteOffset": 12259328
671
+ },
672
+ {
673
+ "name": "param_52",
674
+ "shape": [
675
+ 2560,
676
+ 512
677
+ ],
678
+ "dtype": "uint32",
679
+ "format": "raw",
680
+ "nbytes": 5242880,
681
+ "byteOffset": 12263424
682
+ },
683
+ {
684
+ "name": "param_53",
685
+ "shape": [
686
+ 2560,
687
+ 64
688
+ ],
689
+ "dtype": "float16",
690
+ "format": "raw",
691
+ "nbytes": 327680,
692
+ "byteOffset": 17506304
693
+ },
694
+ {
695
+ "name": "param_54",
696
+ "shape": [
697
+ 2048,
698
+ 512
699
+ ],
700
+ "dtype": "uint32",
701
+ "format": "raw",
702
+ "nbytes": 4194304,
703
+ "byteOffset": 17833984
704
+ },
705
+ {
706
+ "name": "param_55",
707
+ "shape": [
708
+ 2048,
709
+ 64
710
+ ],
711
+ "dtype": "float16",
712
+ "format": "raw",
713
+ "nbytes": 262144,
714
+ "byteOffset": 22028288
715
+ },
716
+ {
717
+ "name": "param_57",
718
+ "shape": [
719
+ 11264,
720
+ 64
721
+ ],
722
+ "dtype": "float16",
723
+ "format": "raw",
724
+ "nbytes": 1441792,
725
+ "byteOffset": 22290432
726
+ }
727
+ ],
728
+ "md5sum": "9b3c1a4f1e14ba3a2c1135fdc2382ef5"
729
+ },
730
+ {
731
+ "dataPath": "params_shard_12.bin",
732
+ "format": "raw-shard",
733
+ "nbytes": 23068672,
734
+ "records": [
735
+ {
736
+ "name": "param_66",
737
+ "shape": [
738
+ 11264,
739
+ 512
740
+ ],
741
+ "dtype": "uint32",
742
+ "format": "raw",
743
+ "nbytes": 23068672,
744
+ "byteOffset": 0
745
+ }
746
+ ],
747
+ "md5sum": "e1f98371d51782630ae701d73990a3f6"
748
+ },
749
+ {
750
+ "dataPath": "params_shard_13.bin",
751
+ "format": "raw-shard",
752
+ "nbytes": 23732224,
753
+ "records": [
754
+ {
755
+ "name": "param_58",
756
+ "shape": [
757
+ 2048,
758
+ 1408
759
+ ],
760
+ "dtype": "uint32",
761
+ "format": "raw",
762
+ "nbytes": 11534336,
763
+ "byteOffset": 0
764
+ },
765
+ {
766
+ "name": "param_59",
767
+ "shape": [
768
+ 2048,
769
+ 176
770
+ ],
771
+ "dtype": "float16",
772
+ "format": "raw",
773
+ "nbytes": 720896,
774
+ "byteOffset": 11534336
775
+ },
776
+ {
777
+ "name": "param_60",
778
+ "shape": [
779
+ 2048
780
+ ],
781
+ "dtype": "float16",
782
+ "format": "raw",
783
+ "nbytes": 4096,
784
+ "byteOffset": 12255232
785
+ },
786
+ {
787
+ "name": "param_61",
788
+ "shape": [
789
+ 2048
790
+ ],
791
+ "dtype": "float16",
792
+ "format": "raw",
793
+ "nbytes": 4096,
794
+ "byteOffset": 12259328
795
+ },
796
+ {
797
+ "name": "param_62",
798
+ "shape": [
799
+ 2560,
800
+ 512
801
+ ],
802
+ "dtype": "uint32",
803
+ "format": "raw",
804
+ "nbytes": 5242880,
805
+ "byteOffset": 12263424
806
+ },
807
+ {
808
+ "name": "param_63",
809
+ "shape": [
810
+ 2560,
811
+ 64
812
+ ],
813
+ "dtype": "float16",
814
+ "format": "raw",
815
+ "nbytes": 327680,
816
+ "byteOffset": 17506304
817
+ },
818
+ {
819
+ "name": "param_64",
820
+ "shape": [
821
+ 2048,
822
+ 512
823
+ ],
824
+ "dtype": "uint32",
825
+ "format": "raw",
826
+ "nbytes": 4194304,
827
+ "byteOffset": 17833984
828
+ },
829
+ {
830
+ "name": "param_65",
831
+ "shape": [
832
+ 2048,
833
+ 64
834
+ ],
835
+ "dtype": "float16",
836
+ "format": "raw",
837
+ "nbytes": 262144,
838
+ "byteOffset": 22028288
839
+ },
840
+ {
841
+ "name": "param_67",
842
+ "shape": [
843
+ 11264,
844
+ 64
845
+ ],
846
+ "dtype": "float16",
847
+ "format": "raw",
848
+ "nbytes": 1441792,
849
+ "byteOffset": 22290432
850
+ }
851
+ ],
852
+ "md5sum": "d2c762958dab75d0594da4331f35a4a7"
853
+ },
854
+ {
855
+ "dataPath": "params_shard_14.bin",
856
+ "format": "raw-shard",
857
+ "nbytes": 23068672,
858
+ "records": [
859
+ {
860
+ "name": "param_76",
861
+ "shape": [
862
+ 11264,
863
+ 512
864
+ ],
865
+ "dtype": "uint32",
866
+ "format": "raw",
867
+ "nbytes": 23068672,
868
+ "byteOffset": 0
869
+ }
870
+ ],
871
+ "md5sum": "69088e0e312e442fc4411a5191349eb1"
872
+ },
873
+ {
874
+ "dataPath": "params_shard_15.bin",
875
+ "format": "raw-shard",
876
+ "nbytes": 23732224,
877
+ "records": [
878
+ {
879
+ "name": "param_68",
880
+ "shape": [
881
+ 2048,
882
+ 1408
883
+ ],
884
+ "dtype": "uint32",
885
+ "format": "raw",
886
+ "nbytes": 11534336,
887
+ "byteOffset": 0
888
+ },
889
+ {
890
+ "name": "param_69",
891
+ "shape": [
892
+ 2048,
893
+ 176
894
+ ],
895
+ "dtype": "float16",
896
+ "format": "raw",
897
+ "nbytes": 720896,
898
+ "byteOffset": 11534336
899
+ },
900
+ {
901
+ "name": "param_70",
902
+ "shape": [
903
+ 2048
904
+ ],
905
+ "dtype": "float16",
906
+ "format": "raw",
907
+ "nbytes": 4096,
908
+ "byteOffset": 12255232
909
+ },
910
+ {
911
+ "name": "param_71",
912
+ "shape": [
913
+ 2048
914
+ ],
915
+ "dtype": "float16",
916
+ "format": "raw",
917
+ "nbytes": 4096,
918
+ "byteOffset": 12259328
919
+ },
920
+ {
921
+ "name": "param_72",
922
+ "shape": [
923
+ 2560,
924
+ 512
925
+ ],
926
+ "dtype": "uint32",
927
+ "format": "raw",
928
+ "nbytes": 5242880,
929
+ "byteOffset": 12263424
930
+ },
931
+ {
932
+ "name": "param_73",
933
+ "shape": [
934
+ 2560,
935
+ 64
936
+ ],
937
+ "dtype": "float16",
938
+ "format": "raw",
939
+ "nbytes": 327680,
940
+ "byteOffset": 17506304
941
+ },
942
+ {
943
+ "name": "param_74",
944
+ "shape": [
945
+ 2048,
946
+ 512
947
+ ],
948
+ "dtype": "uint32",
949
+ "format": "raw",
950
+ "nbytes": 4194304,
951
+ "byteOffset": 17833984
952
+ },
953
+ {
954
+ "name": "param_75",
955
+ "shape": [
956
+ 2048,
957
+ 64
958
+ ],
959
+ "dtype": "float16",
960
+ "format": "raw",
961
+ "nbytes": 262144,
962
+ "byteOffset": 22028288
963
+ },
964
+ {
965
+ "name": "param_77",
966
+ "shape": [
967
+ 11264,
968
+ 64
969
+ ],
970
+ "dtype": "float16",
971
+ "format": "raw",
972
+ "nbytes": 1441792,
973
+ "byteOffset": 22290432
974
+ }
975
+ ],
976
+ "md5sum": "69c939b4e83c1af3bfea2700e55004b5"
977
+ },
978
+ {
979
+ "dataPath": "params_shard_16.bin",
980
+ "format": "raw-shard",
981
+ "nbytes": 23068672,
982
+ "records": [
983
+ {
984
+ "name": "param_86",
985
+ "shape": [
986
+ 11264,
987
+ 512
988
+ ],
989
+ "dtype": "uint32",
990
+ "format": "raw",
991
+ "nbytes": 23068672,
992
+ "byteOffset": 0
993
+ }
994
+ ],
995
+ "md5sum": "ca9cf12a97cbd984c61c9941b3898cfb"
996
+ },
997
+ {
998
+ "dataPath": "params_shard_17.bin",
999
+ "format": "raw-shard",
1000
+ "nbytes": 23732224,
1001
+ "records": [
1002
+ {
1003
+ "name": "param_78",
1004
+ "shape": [
1005
+ 2048,
1006
+ 1408
1007
+ ],
1008
+ "dtype": "uint32",
1009
+ "format": "raw",
1010
+ "nbytes": 11534336,
1011
+ "byteOffset": 0
1012
+ },
1013
+ {
1014
+ "name": "param_79",
1015
+ "shape": [
1016
+ 2048,
1017
+ 176
1018
+ ],
1019
+ "dtype": "float16",
1020
+ "format": "raw",
1021
+ "nbytes": 720896,
1022
+ "byteOffset": 11534336
1023
+ },
1024
+ {
1025
+ "name": "param_80",
1026
+ "shape": [
1027
+ 2048
1028
+ ],
1029
+ "dtype": "float16",
1030
+ "format": "raw",
1031
+ "nbytes": 4096,
1032
+ "byteOffset": 12255232
1033
+ },
1034
+ {
1035
+ "name": "param_81",
1036
+ "shape": [
1037
+ 2048
1038
+ ],
1039
+ "dtype": "float16",
1040
+ "format": "raw",
1041
+ "nbytes": 4096,
1042
+ "byteOffset": 12259328
1043
+ },
1044
+ {
1045
+ "name": "param_82",
1046
+ "shape": [
1047
+ 2560,
1048
+ 512
1049
+ ],
1050
+ "dtype": "uint32",
1051
+ "format": "raw",
1052
+ "nbytes": 5242880,
1053
+ "byteOffset": 12263424
1054
+ },
1055
+ {
1056
+ "name": "param_83",
1057
+ "shape": [
1058
+ 2560,
1059
+ 64
1060
+ ],
1061
+ "dtype": "float16",
1062
+ "format": "raw",
1063
+ "nbytes": 327680,
1064
+ "byteOffset": 17506304
1065
+ },
1066
+ {
1067
+ "name": "param_84",
1068
+ "shape": [
1069
+ 2048,
1070
+ 512
1071
+ ],
1072
+ "dtype": "uint32",
1073
+ "format": "raw",
1074
+ "nbytes": 4194304,
1075
+ "byteOffset": 17833984
1076
+ },
1077
+ {
1078
+ "name": "param_85",
1079
+ "shape": [
1080
+ 2048,
1081
+ 64
1082
+ ],
1083
+ "dtype": "float16",
1084
+ "format": "raw",
1085
+ "nbytes": 262144,
1086
+ "byteOffset": 22028288
1087
+ },
1088
+ {
1089
+ "name": "param_87",
1090
+ "shape": [
1091
+ 11264,
1092
+ 64
1093
+ ],
1094
+ "dtype": "float16",
1095
+ "format": "raw",
1096
+ "nbytes": 1441792,
1097
+ "byteOffset": 22290432
1098
+ }
1099
+ ],
1100
+ "md5sum": "25ea881fe561a139b250510c9b46c6e0"
1101
+ },
1102
+ {
1103
+ "dataPath": "params_shard_18.bin",
1104
+ "format": "raw-shard",
1105
+ "nbytes": 23068672,
1106
+ "records": [
1107
+ {
1108
+ "name": "param_96",
1109
+ "shape": [
1110
+ 11264,
1111
+ 512
1112
+ ],
1113
+ "dtype": "uint32",
1114
+ "format": "raw",
1115
+ "nbytes": 23068672,
1116
+ "byteOffset": 0
1117
+ }
1118
+ ],
1119
+ "md5sum": "7064305c566aa948f7abc25b56602622"
1120
+ },
1121
+ {
1122
+ "dataPath": "params_shard_19.bin",
1123
+ "format": "raw-shard",
1124
+ "nbytes": 23732224,
1125
+ "records": [
1126
+ {
1127
+ "name": "param_88",
1128
+ "shape": [
1129
+ 2048,
1130
+ 1408
1131
+ ],
1132
+ "dtype": "uint32",
1133
+ "format": "raw",
1134
+ "nbytes": 11534336,
1135
+ "byteOffset": 0
1136
+ },
1137
+ {
1138
+ "name": "param_89",
1139
+ "shape": [
1140
+ 2048,
1141
+ 176
1142
+ ],
1143
+ "dtype": "float16",
1144
+ "format": "raw",
1145
+ "nbytes": 720896,
1146
+ "byteOffset": 11534336
1147
+ },
1148
+ {
1149
+ "name": "param_90",
1150
+ "shape": [
1151
+ 2048
1152
+ ],
1153
+ "dtype": "float16",
1154
+ "format": "raw",
1155
+ "nbytes": 4096,
1156
+ "byteOffset": 12255232
1157
+ },
1158
+ {
1159
+ "name": "param_91",
1160
+ "shape": [
1161
+ 2048
1162
+ ],
1163
+ "dtype": "float16",
1164
+ "format": "raw",
1165
+ "nbytes": 4096,
1166
+ "byteOffset": 12259328
1167
+ },
1168
+ {
1169
+ "name": "param_92",
1170
+ "shape": [
1171
+ 2560,
1172
+ 512
1173
+ ],
1174
+ "dtype": "uint32",
1175
+ "format": "raw",
1176
+ "nbytes": 5242880,
1177
+ "byteOffset": 12263424
1178
+ },
1179
+ {
1180
+ "name": "param_93",
1181
+ "shape": [
1182
+ 2560,
1183
+ 64
1184
+ ],
1185
+ "dtype": "float16",
1186
+ "format": "raw",
1187
+ "nbytes": 327680,
1188
+ "byteOffset": 17506304
1189
+ },
1190
+ {
1191
+ "name": "param_94",
1192
+ "shape": [
1193
+ 2048,
1194
+ 512
1195
+ ],
1196
+ "dtype": "uint32",
1197
+ "format": "raw",
1198
+ "nbytes": 4194304,
1199
+ "byteOffset": 17833984
1200
+ },
1201
+ {
1202
+ "name": "param_95",
1203
+ "shape": [
1204
+ 2048,
1205
+ 64
1206
+ ],
1207
+ "dtype": "float16",
1208
+ "format": "raw",
1209
+ "nbytes": 262144,
1210
+ "byteOffset": 22028288
1211
+ },
1212
+ {
1213
+ "name": "param_97",
1214
+ "shape": [
1215
+ 11264,
1216
+ 64
1217
+ ],
1218
+ "dtype": "float16",
1219
+ "format": "raw",
1220
+ "nbytes": 1441792,
1221
+ "byteOffset": 22290432
1222
+ }
1223
+ ],
1224
+ "md5sum": "245cfbcb7725df793900cb47bcbeb17e"
1225
+ },
1226
+ {
1227
+ "dataPath": "params_shard_20.bin",
1228
+ "format": "raw-shard",
1229
+ "nbytes": 23068672,
1230
+ "records": [
1231
+ {
1232
+ "name": "param_106",
1233
+ "shape": [
1234
+ 11264,
1235
+ 512
1236
+ ],
1237
+ "dtype": "uint32",
1238
+ "format": "raw",
1239
+ "nbytes": 23068672,
1240
+ "byteOffset": 0
1241
+ }
1242
+ ],
1243
+ "md5sum": "83c9a0a7d0f166a240eb0fde3a16be65"
1244
+ },
1245
+ {
1246
+ "dataPath": "params_shard_21.bin",
1247
+ "format": "raw-shard",
1248
+ "nbytes": 23732224,
1249
+ "records": [
1250
+ {
1251
+ "name": "param_98",
1252
+ "shape": [
1253
+ 2048,
1254
+ 1408
1255
+ ],
1256
+ "dtype": "uint32",
1257
+ "format": "raw",
1258
+ "nbytes": 11534336,
1259
+ "byteOffset": 0
1260
+ },
1261
+ {
1262
+ "name": "param_99",
1263
+ "shape": [
1264
+ 2048,
1265
+ 176
1266
+ ],
1267
+ "dtype": "float16",
1268
+ "format": "raw",
1269
+ "nbytes": 720896,
1270
+ "byteOffset": 11534336
1271
+ },
1272
+ {
1273
+ "name": "param_100",
1274
+ "shape": [
1275
+ 2048
1276
+ ],
1277
+ "dtype": "float16",
1278
+ "format": "raw",
1279
+ "nbytes": 4096,
1280
+ "byteOffset": 12255232
1281
+ },
1282
+ {
1283
+ "name": "param_101",
1284
+ "shape": [
1285
+ 2048
1286
+ ],
1287
+ "dtype": "float16",
1288
+ "format": "raw",
1289
+ "nbytes": 4096,
1290
+ "byteOffset": 12259328
1291
+ },
1292
+ {
1293
+ "name": "param_102",
1294
+ "shape": [
1295
+ 2560,
1296
+ 512
1297
+ ],
1298
+ "dtype": "uint32",
1299
+ "format": "raw",
1300
+ "nbytes": 5242880,
1301
+ "byteOffset": 12263424
1302
+ },
1303
+ {
1304
+ "name": "param_103",
1305
+ "shape": [
1306
+ 2560,
1307
+ 64
1308
+ ],
1309
+ "dtype": "float16",
1310
+ "format": "raw",
1311
+ "nbytes": 327680,
1312
+ "byteOffset": 17506304
1313
+ },
1314
+ {
1315
+ "name": "param_104",
1316
+ "shape": [
1317
+ 2048,
1318
+ 512
1319
+ ],
1320
+ "dtype": "uint32",
1321
+ "format": "raw",
1322
+ "nbytes": 4194304,
1323
+ "byteOffset": 17833984
1324
+ },
1325
+ {
1326
+ "name": "param_105",
1327
+ "shape": [
1328
+ 2048,
1329
+ 64
1330
+ ],
1331
+ "dtype": "float16",
1332
+ "format": "raw",
1333
+ "nbytes": 262144,
1334
+ "byteOffset": 22028288
1335
+ },
1336
+ {
1337
+ "name": "param_107",
1338
+ "shape": [
1339
+ 11264,
1340
+ 64
1341
+ ],
1342
+ "dtype": "float16",
1343
+ "format": "raw",
1344
+ "nbytes": 1441792,
1345
+ "byteOffset": 22290432
1346
+ }
1347
+ ],
1348
+ "md5sum": "732c3f7e5ae9bc02c565be331d5b8c85"
1349
+ },
1350
+ {
1351
+ "dataPath": "params_shard_22.bin",
1352
+ "format": "raw-shard",
1353
+ "nbytes": 23068672,
1354
+ "records": [
1355
+ {
1356
+ "name": "param_116",
1357
+ "shape": [
1358
+ 11264,
1359
+ 512
1360
+ ],
1361
+ "dtype": "uint32",
1362
+ "format": "raw",
1363
+ "nbytes": 23068672,
1364
+ "byteOffset": 0
1365
+ }
1366
+ ],
1367
+ "md5sum": "9ecff164cf9c7b9e57319112d58bf085"
1368
+ },
1369
+ {
1370
+ "dataPath": "params_shard_23.bin",
1371
+ "format": "raw-shard",
1372
+ "nbytes": 23732224,
1373
+ "records": [
1374
+ {
1375
+ "name": "param_108",
1376
+ "shape": [
1377
+ 2048,
1378
+ 1408
1379
+ ],
1380
+ "dtype": "uint32",
1381
+ "format": "raw",
1382
+ "nbytes": 11534336,
1383
+ "byteOffset": 0
1384
+ },
1385
+ {
1386
+ "name": "param_109",
1387
+ "shape": [
1388
+ 2048,
1389
+ 176
1390
+ ],
1391
+ "dtype": "float16",
1392
+ "format": "raw",
1393
+ "nbytes": 720896,
1394
+ "byteOffset": 11534336
1395
+ },
1396
+ {
1397
+ "name": "param_110",
1398
+ "shape": [
1399
+ 2048
1400
+ ],
1401
+ "dtype": "float16",
1402
+ "format": "raw",
1403
+ "nbytes": 4096,
1404
+ "byteOffset": 12255232
1405
+ },
1406
+ {
1407
+ "name": "param_111",
1408
+ "shape": [
1409
+ 2048
1410
+ ],
1411
+ "dtype": "float16",
1412
+ "format": "raw",
1413
+ "nbytes": 4096,
1414
+ "byteOffset": 12259328
1415
+ },
1416
+ {
1417
+ "name": "param_112",
1418
+ "shape": [
1419
+ 2560,
1420
+ 512
1421
+ ],
1422
+ "dtype": "uint32",
1423
+ "format": "raw",
1424
+ "nbytes": 5242880,
1425
+ "byteOffset": 12263424
1426
+ },
1427
+ {
1428
+ "name": "param_113",
1429
+ "shape": [
1430
+ 2560,
1431
+ 64
1432
+ ],
1433
+ "dtype": "float16",
1434
+ "format": "raw",
1435
+ "nbytes": 327680,
1436
+ "byteOffset": 17506304
1437
+ },
1438
+ {
1439
+ "name": "param_114",
1440
+ "shape": [
1441
+ 2048,
1442
+ 512
1443
+ ],
1444
+ "dtype": "uint32",
1445
+ "format": "raw",
1446
+ "nbytes": 4194304,
1447
+ "byteOffset": 17833984
1448
+ },
1449
+ {
1450
+ "name": "param_115",
1451
+ "shape": [
1452
+ 2048,
1453
+ 64
1454
+ ],
1455
+ "dtype": "float16",
1456
+ "format": "raw",
1457
+ "nbytes": 262144,
1458
+ "byteOffset": 22028288
1459
+ },
1460
+ {
1461
+ "name": "param_117",
1462
+ "shape": [
1463
+ 11264,
1464
+ 64
1465
+ ],
1466
+ "dtype": "float16",
1467
+ "format": "raw",
1468
+ "nbytes": 1441792,
1469
+ "byteOffset": 22290432
1470
+ }
1471
+ ],
1472
+ "md5sum": "1fa6090d93a0e8ffb86cd9d9818a4c49"
1473
+ },
1474
+ {
1475
+ "dataPath": "params_shard_24.bin",
1476
+ "format": "raw-shard",
1477
+ "nbytes": 23068672,
1478
+ "records": [
1479
+ {
1480
+ "name": "param_126",
1481
+ "shape": [
1482
+ 11264,
1483
+ 512
1484
+ ],
1485
+ "dtype": "uint32",
1486
+ "format": "raw",
1487
+ "nbytes": 23068672,
1488
+ "byteOffset": 0
1489
+ }
1490
+ ],
1491
+ "md5sum": "215b1963a5f7978f12dea4c5d062fee7"
1492
+ },
1493
+ {
1494
+ "dataPath": "params_shard_25.bin",
1495
+ "format": "raw-shard",
1496
+ "nbytes": 23732224,
1497
+ "records": [
1498
+ {
1499
+ "name": "param_118",
1500
+ "shape": [
1501
+ 2048,
1502
+ 1408
1503
+ ],
1504
+ "dtype": "uint32",
1505
+ "format": "raw",
1506
+ "nbytes": 11534336,
1507
+ "byteOffset": 0
1508
+ },
1509
+ {
1510
+ "name": "param_119",
1511
+ "shape": [
1512
+ 2048,
1513
+ 176
1514
+ ],
1515
+ "dtype": "float16",
1516
+ "format": "raw",
1517
+ "nbytes": 720896,
1518
+ "byteOffset": 11534336
1519
+ },
1520
+ {
1521
+ "name": "param_120",
1522
+ "shape": [
1523
+ 2048
1524
+ ],
1525
+ "dtype": "float16",
1526
+ "format": "raw",
1527
+ "nbytes": 4096,
1528
+ "byteOffset": 12255232
1529
+ },
1530
+ {
1531
+ "name": "param_121",
1532
+ "shape": [
1533
+ 2048
1534
+ ],
1535
+ "dtype": "float16",
1536
+ "format": "raw",
1537
+ "nbytes": 4096,
1538
+ "byteOffset": 12259328
1539
+ },
1540
+ {
1541
+ "name": "param_122",
1542
+ "shape": [
1543
+ 2560,
1544
+ 512
1545
+ ],
1546
+ "dtype": "uint32",
1547
+ "format": "raw",
1548
+ "nbytes": 5242880,
1549
+ "byteOffset": 12263424
1550
+ },
1551
+ {
1552
+ "name": "param_123",
1553
+ "shape": [
1554
+ 2560,
1555
+ 64
1556
+ ],
1557
+ "dtype": "float16",
1558
+ "format": "raw",
1559
+ "nbytes": 327680,
1560
+ "byteOffset": 17506304
1561
+ },
1562
+ {
1563
+ "name": "param_124",
1564
+ "shape": [
1565
+ 2048,
1566
+ 512
1567
+ ],
1568
+ "dtype": "uint32",
1569
+ "format": "raw",
1570
+ "nbytes": 4194304,
1571
+ "byteOffset": 17833984
1572
+ },
1573
+ {
1574
+ "name": "param_125",
1575
+ "shape": [
1576
+ 2048,
1577
+ 64
1578
+ ],
1579
+ "dtype": "float16",
1580
+ "format": "raw",
1581
+ "nbytes": 262144,
1582
+ "byteOffset": 22028288
1583
+ },
1584
+ {
1585
+ "name": "param_127",
1586
+ "shape": [
1587
+ 11264,
1588
+ 64
1589
+ ],
1590
+ "dtype": "float16",
1591
+ "format": "raw",
1592
+ "nbytes": 1441792,
1593
+ "byteOffset": 22290432
1594
+ }
1595
+ ],
1596
+ "md5sum": "818fa3d699d757e7b4b92d4929d2725b"
1597
+ },
1598
+ {
1599
+ "dataPath": "params_shard_26.bin",
1600
+ "format": "raw-shard",
1601
+ "nbytes": 23068672,
1602
+ "records": [
1603
+ {
1604
+ "name": "param_136",
1605
+ "shape": [
1606
+ 11264,
1607
+ 512
1608
+ ],
1609
+ "dtype": "uint32",
1610
+ "format": "raw",
1611
+ "nbytes": 23068672,
1612
+ "byteOffset": 0
1613
+ }
1614
+ ],
1615
+ "md5sum": "41ecd733af9e18471f211d6267730e7b"
1616
+ },
1617
+ {
1618
+ "dataPath": "params_shard_27.bin",
1619
+ "format": "raw-shard",
1620
+ "nbytes": 23732224,
1621
+ "records": [
1622
+ {
1623
+ "name": "param_128",
1624
+ "shape": [
1625
+ 2048,
1626
+ 1408
1627
+ ],
1628
+ "dtype": "uint32",
1629
+ "format": "raw",
1630
+ "nbytes": 11534336,
1631
+ "byteOffset": 0
1632
+ },
1633
+ {
1634
+ "name": "param_129",
1635
+ "shape": [
1636
+ 2048,
1637
+ 176
1638
+ ],
1639
+ "dtype": "float16",
1640
+ "format": "raw",
1641
+ "nbytes": 720896,
1642
+ "byteOffset": 11534336
1643
+ },
1644
+ {
1645
+ "name": "param_130",
1646
+ "shape": [
1647
+ 2048
1648
+ ],
1649
+ "dtype": "float16",
1650
+ "format": "raw",
1651
+ "nbytes": 4096,
1652
+ "byteOffset": 12255232
1653
+ },
1654
+ {
1655
+ "name": "param_131",
1656
+ "shape": [
1657
+ 2048
1658
+ ],
1659
+ "dtype": "float16",
1660
+ "format": "raw",
1661
+ "nbytes": 4096,
1662
+ "byteOffset": 12259328
1663
+ },
1664
+ {
1665
+ "name": "param_132",
1666
+ "shape": [
1667
+ 2560,
1668
+ 512
1669
+ ],
1670
+ "dtype": "uint32",
1671
+ "format": "raw",
1672
+ "nbytes": 5242880,
1673
+ "byteOffset": 12263424
1674
+ },
1675
+ {
1676
+ "name": "param_133",
1677
+ "shape": [
1678
+ 2560,
1679
+ 64
1680
+ ],
1681
+ "dtype": "float16",
1682
+ "format": "raw",
1683
+ "nbytes": 327680,
1684
+ "byteOffset": 17506304
1685
+ },
1686
+ {
1687
+ "name": "param_134",
1688
+ "shape": [
1689
+ 2048,
1690
+ 512
1691
+ ],
1692
+ "dtype": "uint32",
1693
+ "format": "raw",
1694
+ "nbytes": 4194304,
1695
+ "byteOffset": 17833984
1696
+ },
1697
+ {
1698
+ "name": "param_135",
1699
+ "shape": [
1700
+ 2048,
1701
+ 64
1702
+ ],
1703
+ "dtype": "float16",
1704
+ "format": "raw",
1705
+ "nbytes": 262144,
1706
+ "byteOffset": 22028288
1707
+ },
1708
+ {
1709
+ "name": "param_137",
1710
+ "shape": [
1711
+ 11264,
1712
+ 64
1713
+ ],
1714
+ "dtype": "float16",
1715
+ "format": "raw",
1716
+ "nbytes": 1441792,
1717
+ "byteOffset": 22290432
1718
+ }
1719
+ ],
1720
+ "md5sum": "15182cb3ea8b4aa354d9a6ff37de3265"
1721
+ },
1722
+ {
1723
+ "dataPath": "params_shard_28.bin",
1724
+ "format": "raw-shard",
1725
+ "nbytes": 23068672,
1726
+ "records": [
1727
+ {
1728
+ "name": "param_146",
1729
+ "shape": [
1730
+ 11264,
1731
+ 512
1732
+ ],
1733
+ "dtype": "uint32",
1734
+ "format": "raw",
1735
+ "nbytes": 23068672,
1736
+ "byteOffset": 0
1737
+ }
1738
+ ],
1739
+ "md5sum": "fe9c6c48f3d32c21048aef8a434fecf0"
1740
+ },
1741
+ {
1742
+ "dataPath": "params_shard_29.bin",
1743
+ "format": "raw-shard",
1744
+ "nbytes": 23732224,
1745
+ "records": [
1746
+ {
1747
+ "name": "param_138",
1748
+ "shape": [
1749
+ 2048,
1750
+ 1408
1751
+ ],
1752
+ "dtype": "uint32",
1753
+ "format": "raw",
1754
+ "nbytes": 11534336,
1755
+ "byteOffset": 0
1756
+ },
1757
+ {
1758
+ "name": "param_139",
1759
+ "shape": [
1760
+ 2048,
1761
+ 176
1762
+ ],
1763
+ "dtype": "float16",
1764
+ "format": "raw",
1765
+ "nbytes": 720896,
1766
+ "byteOffset": 11534336
1767
+ },
1768
+ {
1769
+ "name": "param_140",
1770
+ "shape": [
1771
+ 2048
1772
+ ],
1773
+ "dtype": "float16",
1774
+ "format": "raw",
1775
+ "nbytes": 4096,
1776
+ "byteOffset": 12255232
1777
+ },
1778
+ {
1779
+ "name": "param_141",
1780
+ "shape": [
1781
+ 2048
1782
+ ],
1783
+ "dtype": "float16",
1784
+ "format": "raw",
1785
+ "nbytes": 4096,
1786
+ "byteOffset": 12259328
1787
+ },
1788
+ {
1789
+ "name": "param_142",
1790
+ "shape": [
1791
+ 2560,
1792
+ 512
1793
+ ],
1794
+ "dtype": "uint32",
1795
+ "format": "raw",
1796
+ "nbytes": 5242880,
1797
+ "byteOffset": 12263424
1798
+ },
1799
+ {
1800
+ "name": "param_143",
1801
+ "shape": [
1802
+ 2560,
1803
+ 64
1804
+ ],
1805
+ "dtype": "float16",
1806
+ "format": "raw",
1807
+ "nbytes": 327680,
1808
+ "byteOffset": 17506304
1809
+ },
1810
+ {
1811
+ "name": "param_144",
1812
+ "shape": [
1813
+ 2048,
1814
+ 512
1815
+ ],
1816
+ "dtype": "uint32",
1817
+ "format": "raw",
1818
+ "nbytes": 4194304,
1819
+ "byteOffset": 17833984
1820
+ },
1821
+ {
1822
+ "name": "param_145",
1823
+ "shape": [
1824
+ 2048,
1825
+ 64
1826
+ ],
1827
+ "dtype": "float16",
1828
+ "format": "raw",
1829
+ "nbytes": 262144,
1830
+ "byteOffset": 22028288
1831
+ },
1832
+ {
1833
+ "name": "param_147",
1834
+ "shape": [
1835
+ 11264,
1836
+ 64
1837
+ ],
1838
+ "dtype": "float16",
1839
+ "format": "raw",
1840
+ "nbytes": 1441792,
1841
+ "byteOffset": 22290432
1842
+ }
1843
+ ],
1844
+ "md5sum": "2447cab0e3cc916c1a7768cb2496f4d3"
1845
+ },
1846
+ {
1847
+ "dataPath": "params_shard_30.bin",
1848
+ "format": "raw-shard",
1849
+ "nbytes": 23068672,
1850
+ "records": [
1851
+ {
1852
+ "name": "param_156",
1853
+ "shape": [
1854
+ 11264,
1855
+ 512
1856
+ ],
1857
+ "dtype": "uint32",
1858
+ "format": "raw",
1859
+ "nbytes": 23068672,
1860
+ "byteOffset": 0
1861
+ }
1862
+ ],
1863
+ "md5sum": "bcb5288102280f112044ea8676bafd6e"
1864
+ },
1865
+ {
1866
+ "dataPath": "params_shard_31.bin",
1867
+ "format": "raw-shard",
1868
+ "nbytes": 23732224,
1869
+ "records": [
1870
+ {
1871
+ "name": "param_148",
1872
+ "shape": [
1873
+ 2048,
1874
+ 1408
1875
+ ],
1876
+ "dtype": "uint32",
1877
+ "format": "raw",
1878
+ "nbytes": 11534336,
1879
+ "byteOffset": 0
1880
+ },
1881
+ {
1882
+ "name": "param_149",
1883
+ "shape": [
1884
+ 2048,
1885
+ 176
1886
+ ],
1887
+ "dtype": "float16",
1888
+ "format": "raw",
1889
+ "nbytes": 720896,
1890
+ "byteOffset": 11534336
1891
+ },
1892
+ {
1893
+ "name": "param_150",
1894
+ "shape": [
1895
+ 2048
1896
+ ],
1897
+ "dtype": "float16",
1898
+ "format": "raw",
1899
+ "nbytes": 4096,
1900
+ "byteOffset": 12255232
1901
+ },
1902
+ {
1903
+ "name": "param_151",
1904
+ "shape": [
1905
+ 2048
1906
+ ],
1907
+ "dtype": "float16",
1908
+ "format": "raw",
1909
+ "nbytes": 4096,
1910
+ "byteOffset": 12259328
1911
+ },
1912
+ {
1913
+ "name": "param_152",
1914
+ "shape": [
1915
+ 2560,
1916
+ 512
1917
+ ],
1918
+ "dtype": "uint32",
1919
+ "format": "raw",
1920
+ "nbytes": 5242880,
1921
+ "byteOffset": 12263424
1922
+ },
1923
+ {
1924
+ "name": "param_153",
1925
+ "shape": [
1926
+ 2560,
1927
+ 64
1928
+ ],
1929
+ "dtype": "float16",
1930
+ "format": "raw",
1931
+ "nbytes": 327680,
1932
+ "byteOffset": 17506304
1933
+ },
1934
+ {
1935
+ "name": "param_154",
1936
+ "shape": [
1937
+ 2048,
1938
+ 512
1939
+ ],
1940
+ "dtype": "uint32",
1941
+ "format": "raw",
1942
+ "nbytes": 4194304,
1943
+ "byteOffset": 17833984
1944
+ },
1945
+ {
1946
+ "name": "param_155",
1947
+ "shape": [
1948
+ 2048,
1949
+ 64
1950
+ ],
1951
+ "dtype": "float16",
1952
+ "format": "raw",
1953
+ "nbytes": 262144,
1954
+ "byteOffset": 22028288
1955
+ },
1956
+ {
1957
+ "name": "param_157",
1958
+ "shape": [
1959
+ 11264,
1960
+ 64
1961
+ ],
1962
+ "dtype": "float16",
1963
+ "format": "raw",
1964
+ "nbytes": 1441792,
1965
+ "byteOffset": 22290432
1966
+ }
1967
+ ],
1968
+ "md5sum": "e26d2261435d7c2f5ad54109b0d63a86"
1969
+ },
1970
+ {
1971
+ "dataPath": "params_shard_32.bin",
1972
+ "format": "raw-shard",
1973
+ "nbytes": 23068672,
1974
+ "records": [
1975
+ {
1976
+ "name": "param_166",
1977
+ "shape": [
1978
+ 11264,
1979
+ 512
1980
+ ],
1981
+ "dtype": "uint32",
1982
+ "format": "raw",
1983
+ "nbytes": 23068672,
1984
+ "byteOffset": 0
1985
+ }
1986
+ ],
1987
+ "md5sum": "be06a966ee535be888c95f513b8316b8"
1988
+ },
1989
+ {
1990
+ "dataPath": "params_shard_33.bin",
1991
+ "format": "raw-shard",
1992
+ "nbytes": 23732224,
1993
+ "records": [
1994
+ {
1995
+ "name": "param_158",
1996
+ "shape": [
1997
+ 2048,
1998
+ 1408
1999
+ ],
2000
+ "dtype": "uint32",
2001
+ "format": "raw",
2002
+ "nbytes": 11534336,
2003
+ "byteOffset": 0
2004
+ },
2005
+ {
2006
+ "name": "param_159",
2007
+ "shape": [
2008
+ 2048,
2009
+ 176
2010
+ ],
2011
+ "dtype": "float16",
2012
+ "format": "raw",
2013
+ "nbytes": 720896,
2014
+ "byteOffset": 11534336
2015
+ },
2016
+ {
2017
+ "name": "param_160",
2018
+ "shape": [
2019
+ 2048
2020
+ ],
2021
+ "dtype": "float16",
2022
+ "format": "raw",
2023
+ "nbytes": 4096,
2024
+ "byteOffset": 12255232
2025
+ },
2026
+ {
2027
+ "name": "param_161",
2028
+ "shape": [
2029
+ 2048
2030
+ ],
2031
+ "dtype": "float16",
2032
+ "format": "raw",
2033
+ "nbytes": 4096,
2034
+ "byteOffset": 12259328
2035
+ },
2036
+ {
2037
+ "name": "param_162",
2038
+ "shape": [
2039
+ 2560,
2040
+ 512
2041
+ ],
2042
+ "dtype": "uint32",
2043
+ "format": "raw",
2044
+ "nbytes": 5242880,
2045
+ "byteOffset": 12263424
2046
+ },
2047
+ {
2048
+ "name": "param_163",
2049
+ "shape": [
2050
+ 2560,
2051
+ 64
2052
+ ],
2053
+ "dtype": "float16",
2054
+ "format": "raw",
2055
+ "nbytes": 327680,
2056
+ "byteOffset": 17506304
2057
+ },
2058
+ {
2059
+ "name": "param_164",
2060
+ "shape": [
2061
+ 2048,
2062
+ 512
2063
+ ],
2064
+ "dtype": "uint32",
2065
+ "format": "raw",
2066
+ "nbytes": 4194304,
2067
+ "byteOffset": 17833984
2068
+ },
2069
+ {
2070
+ "name": "param_165",
2071
+ "shape": [
2072
+ 2048,
2073
+ 64
2074
+ ],
2075
+ "dtype": "float16",
2076
+ "format": "raw",
2077
+ "nbytes": 262144,
2078
+ "byteOffset": 22028288
2079
+ },
2080
+ {
2081
+ "name": "param_167",
2082
+ "shape": [
2083
+ 11264,
2084
+ 64
2085
+ ],
2086
+ "dtype": "float16",
2087
+ "format": "raw",
2088
+ "nbytes": 1441792,
2089
+ "byteOffset": 22290432
2090
+ }
2091
+ ],
2092
+ "md5sum": "a5677009d30fc124af2c78dc6e51b3de"
2093
+ },
2094
+ {
2095
+ "dataPath": "params_shard_34.bin",
2096
+ "format": "raw-shard",
2097
+ "nbytes": 23068672,
2098
+ "records": [
2099
+ {
2100
+ "name": "param_176",
2101
+ "shape": [
2102
+ 11264,
2103
+ 512
2104
+ ],
2105
+ "dtype": "uint32",
2106
+ "format": "raw",
2107
+ "nbytes": 23068672,
2108
+ "byteOffset": 0
2109
+ }
2110
+ ],
2111
+ "md5sum": "aab20dd6cc84c3cfa92c79b386106b70"
2112
+ },
2113
+ {
2114
+ "dataPath": "params_shard_35.bin",
2115
+ "format": "raw-shard",
2116
+ "nbytes": 23732224,
2117
+ "records": [
2118
+ {
2119
+ "name": "param_168",
2120
+ "shape": [
2121
+ 2048,
2122
+ 1408
2123
+ ],
2124
+ "dtype": "uint32",
2125
+ "format": "raw",
2126
+ "nbytes": 11534336,
2127
+ "byteOffset": 0
2128
+ },
2129
+ {
2130
+ "name": "param_169",
2131
+ "shape": [
2132
+ 2048,
2133
+ 176
2134
+ ],
2135
+ "dtype": "float16",
2136
+ "format": "raw",
2137
+ "nbytes": 720896,
2138
+ "byteOffset": 11534336
2139
+ },
2140
+ {
2141
+ "name": "param_170",
2142
+ "shape": [
2143
+ 2048
2144
+ ],
2145
+ "dtype": "float16",
2146
+ "format": "raw",
2147
+ "nbytes": 4096,
2148
+ "byteOffset": 12255232
2149
+ },
2150
+ {
2151
+ "name": "param_171",
2152
+ "shape": [
2153
+ 2048
2154
+ ],
2155
+ "dtype": "float16",
2156
+ "format": "raw",
2157
+ "nbytes": 4096,
2158
+ "byteOffset": 12259328
2159
+ },
2160
+ {
2161
+ "name": "param_172",
2162
+ "shape": [
2163
+ 2560,
2164
+ 512
2165
+ ],
2166
+ "dtype": "uint32",
2167
+ "format": "raw",
2168
+ "nbytes": 5242880,
2169
+ "byteOffset": 12263424
2170
+ },
2171
+ {
2172
+ "name": "param_173",
2173
+ "shape": [
2174
+ 2560,
2175
+ 64
2176
+ ],
2177
+ "dtype": "float16",
2178
+ "format": "raw",
2179
+ "nbytes": 327680,
2180
+ "byteOffset": 17506304
2181
+ },
2182
+ {
2183
+ "name": "param_174",
2184
+ "shape": [
2185
+ 2048,
2186
+ 512
2187
+ ],
2188
+ "dtype": "uint32",
2189
+ "format": "raw",
2190
+ "nbytes": 4194304,
2191
+ "byteOffset": 17833984
2192
+ },
2193
+ {
2194
+ "name": "param_175",
2195
+ "shape": [
2196
+ 2048,
2197
+ 64
2198
+ ],
2199
+ "dtype": "float16",
2200
+ "format": "raw",
2201
+ "nbytes": 262144,
2202
+ "byteOffset": 22028288
2203
+ },
2204
+ {
2205
+ "name": "param_177",
2206
+ "shape": [
2207
+ 11264,
2208
+ 64
2209
+ ],
2210
+ "dtype": "float16",
2211
+ "format": "raw",
2212
+ "nbytes": 1441792,
2213
+ "byteOffset": 22290432
2214
+ }
2215
+ ],
2216
+ "md5sum": "efc7e05bf326693ca73258b79d93fbd5"
2217
+ },
2218
+ {
2219
+ "dataPath": "params_shard_36.bin",
2220
+ "format": "raw-shard",
2221
+ "nbytes": 23068672,
2222
+ "records": [
2223
+ {
2224
+ "name": "param_186",
2225
+ "shape": [
2226
+ 11264,
2227
+ 512
2228
+ ],
2229
+ "dtype": "uint32",
2230
+ "format": "raw",
2231
+ "nbytes": 23068672,
2232
+ "byteOffset": 0
2233
+ }
2234
+ ],
2235
+ "md5sum": "5a3598aa992746a5d74aad0c3666322b"
2236
+ },
2237
+ {
2238
+ "dataPath": "params_shard_37.bin",
2239
+ "format": "raw-shard",
2240
+ "nbytes": 23732224,
2241
+ "records": [
2242
+ {
2243
+ "name": "param_178",
2244
+ "shape": [
2245
+ 2048,
2246
+ 1408
2247
+ ],
2248
+ "dtype": "uint32",
2249
+ "format": "raw",
2250
+ "nbytes": 11534336,
2251
+ "byteOffset": 0
2252
+ },
2253
+ {
2254
+ "name": "param_179",
2255
+ "shape": [
2256
+ 2048,
2257
+ 176
2258
+ ],
2259
+ "dtype": "float16",
2260
+ "format": "raw",
2261
+ "nbytes": 720896,
2262
+ "byteOffset": 11534336
2263
+ },
2264
+ {
2265
+ "name": "param_180",
2266
+ "shape": [
2267
+ 2048
2268
+ ],
2269
+ "dtype": "float16",
2270
+ "format": "raw",
2271
+ "nbytes": 4096,
2272
+ "byteOffset": 12255232
2273
+ },
2274
+ {
2275
+ "name": "param_181",
2276
+ "shape": [
2277
+ 2048
2278
+ ],
2279
+ "dtype": "float16",
2280
+ "format": "raw",
2281
+ "nbytes": 4096,
2282
+ "byteOffset": 12259328
2283
+ },
2284
+ {
2285
+ "name": "param_182",
2286
+ "shape": [
2287
+ 2560,
2288
+ 512
2289
+ ],
2290
+ "dtype": "uint32",
2291
+ "format": "raw",
2292
+ "nbytes": 5242880,
2293
+ "byteOffset": 12263424
2294
+ },
2295
+ {
2296
+ "name": "param_183",
2297
+ "shape": [
2298
+ 2560,
2299
+ 64
2300
+ ],
2301
+ "dtype": "float16",
2302
+ "format": "raw",
2303
+ "nbytes": 327680,
2304
+ "byteOffset": 17506304
2305
+ },
2306
+ {
2307
+ "name": "param_184",
2308
+ "shape": [
2309
+ 2048,
2310
+ 512
2311
+ ],
2312
+ "dtype": "uint32",
2313
+ "format": "raw",
2314
+ "nbytes": 4194304,
2315
+ "byteOffset": 17833984
2316
+ },
2317
+ {
2318
+ "name": "param_185",
2319
+ "shape": [
2320
+ 2048,
2321
+ 64
2322
+ ],
2323
+ "dtype": "float16",
2324
+ "format": "raw",
2325
+ "nbytes": 262144,
2326
+ "byteOffset": 22028288
2327
+ },
2328
+ {
2329
+ "name": "param_187",
2330
+ "shape": [
2331
+ 11264,
2332
+ 64
2333
+ ],
2334
+ "dtype": "float16",
2335
+ "format": "raw",
2336
+ "nbytes": 1441792,
2337
+ "byteOffset": 22290432
2338
+ }
2339
+ ],
2340
+ "md5sum": "2166ec1ae930640798150b066b8680aa"
2341
+ },
2342
+ {
2343
+ "dataPath": "params_shard_38.bin",
2344
+ "format": "raw-shard",
2345
+ "nbytes": 23068672,
2346
+ "records": [
2347
+ {
2348
+ "name": "param_196",
2349
+ "shape": [
2350
+ 11264,
2351
+ 512
2352
+ ],
2353
+ "dtype": "uint32",
2354
+ "format": "raw",
2355
+ "nbytes": 23068672,
2356
+ "byteOffset": 0
2357
+ }
2358
+ ],
2359
+ "md5sum": "4294e532612bbf36f79aeb5b72991fde"
2360
+ },
2361
+ {
2362
+ "dataPath": "params_shard_39.bin",
2363
+ "format": "raw-shard",
2364
+ "nbytes": 23732224,
2365
+ "records": [
2366
+ {
2367
+ "name": "param_188",
2368
+ "shape": [
2369
+ 2048,
2370
+ 1408
2371
+ ],
2372
+ "dtype": "uint32",
2373
+ "format": "raw",
2374
+ "nbytes": 11534336,
2375
+ "byteOffset": 0
2376
+ },
2377
+ {
2378
+ "name": "param_189",
2379
+ "shape": [
2380
+ 2048,
2381
+ 176
2382
+ ],
2383
+ "dtype": "float16",
2384
+ "format": "raw",
2385
+ "nbytes": 720896,
2386
+ "byteOffset": 11534336
2387
+ },
2388
+ {
2389
+ "name": "param_190",
2390
+ "shape": [
2391
+ 2048
2392
+ ],
2393
+ "dtype": "float16",
2394
+ "format": "raw",
2395
+ "nbytes": 4096,
2396
+ "byteOffset": 12255232
2397
+ },
2398
+ {
2399
+ "name": "param_191",
2400
+ "shape": [
2401
+ 2048
2402
+ ],
2403
+ "dtype": "float16",
2404
+ "format": "raw",
2405
+ "nbytes": 4096,
2406
+ "byteOffset": 12259328
2407
+ },
2408
+ {
2409
+ "name": "param_192",
2410
+ "shape": [
2411
+ 2560,
2412
+ 512
2413
+ ],
2414
+ "dtype": "uint32",
2415
+ "format": "raw",
2416
+ "nbytes": 5242880,
2417
+ "byteOffset": 12263424
2418
+ },
2419
+ {
2420
+ "name": "param_193",
2421
+ "shape": [
2422
+ 2560,
2423
+ 64
2424
+ ],
2425
+ "dtype": "float16",
2426
+ "format": "raw",
2427
+ "nbytes": 327680,
2428
+ "byteOffset": 17506304
2429
+ },
2430
+ {
2431
+ "name": "param_194",
2432
+ "shape": [
2433
+ 2048,
2434
+ 512
2435
+ ],
2436
+ "dtype": "uint32",
2437
+ "format": "raw",
2438
+ "nbytes": 4194304,
2439
+ "byteOffset": 17833984
2440
+ },
2441
+ {
2442
+ "name": "param_195",
2443
+ "shape": [
2444
+ 2048,
2445
+ 64
2446
+ ],
2447
+ "dtype": "float16",
2448
+ "format": "raw",
2449
+ "nbytes": 262144,
2450
+ "byteOffset": 22028288
2451
+ },
2452
+ {
2453
+ "name": "param_197",
2454
+ "shape": [
2455
+ 11264,
2456
+ 64
2457
+ ],
2458
+ "dtype": "float16",
2459
+ "format": "raw",
2460
+ "nbytes": 1441792,
2461
+ "byteOffset": 22290432
2462
+ }
2463
+ ],
2464
+ "md5sum": "fc92094332eb29686d7d58aa29246b2c"
2465
+ },
2466
+ {
2467
+ "dataPath": "params_shard_40.bin",
2468
+ "format": "raw-shard",
2469
+ "nbytes": 23068672,
2470
+ "records": [
2471
+ {
2472
+ "name": "param_206",
2473
+ "shape": [
2474
+ 11264,
2475
+ 512
2476
+ ],
2477
+ "dtype": "uint32",
2478
+ "format": "raw",
2479
+ "nbytes": 23068672,
2480
+ "byteOffset": 0
2481
+ }
2482
+ ],
2483
+ "md5sum": "c8a64f0a4ea8c4bdf3d77cf4471248d6"
2484
+ },
2485
+ {
2486
+ "dataPath": "params_shard_41.bin",
2487
+ "format": "raw-shard",
2488
+ "nbytes": 23732224,
2489
+ "records": [
2490
+ {
2491
+ "name": "param_198",
2492
+ "shape": [
2493
+ 2048,
2494
+ 1408
2495
+ ],
2496
+ "dtype": "uint32",
2497
+ "format": "raw",
2498
+ "nbytes": 11534336,
2499
+ "byteOffset": 0
2500
+ },
2501
+ {
2502
+ "name": "param_199",
2503
+ "shape": [
2504
+ 2048,
2505
+ 176
2506
+ ],
2507
+ "dtype": "float16",
2508
+ "format": "raw",
2509
+ "nbytes": 720896,
2510
+ "byteOffset": 11534336
2511
+ },
2512
+ {
2513
+ "name": "param_200",
2514
+ "shape": [
2515
+ 2048
2516
+ ],
2517
+ "dtype": "float16",
2518
+ "format": "raw",
2519
+ "nbytes": 4096,
2520
+ "byteOffset": 12255232
2521
+ },
2522
+ {
2523
+ "name": "param_201",
2524
+ "shape": [
2525
+ 2048
2526
+ ],
2527
+ "dtype": "float16",
2528
+ "format": "raw",
2529
+ "nbytes": 4096,
2530
+ "byteOffset": 12259328
2531
+ },
2532
+ {
2533
+ "name": "param_202",
2534
+ "shape": [
2535
+ 2560,
2536
+ 512
2537
+ ],
2538
+ "dtype": "uint32",
2539
+ "format": "raw",
2540
+ "nbytes": 5242880,
2541
+ "byteOffset": 12263424
2542
+ },
2543
+ {
2544
+ "name": "param_203",
2545
+ "shape": [
2546
+ 2560,
2547
+ 64
2548
+ ],
2549
+ "dtype": "float16",
2550
+ "format": "raw",
2551
+ "nbytes": 327680,
2552
+ "byteOffset": 17506304
2553
+ },
2554
+ {
2555
+ "name": "param_204",
2556
+ "shape": [
2557
+ 2048,
2558
+ 512
2559
+ ],
2560
+ "dtype": "uint32",
2561
+ "format": "raw",
2562
+ "nbytes": 4194304,
2563
+ "byteOffset": 17833984
2564
+ },
2565
+ {
2566
+ "name": "param_205",
2567
+ "shape": [
2568
+ 2048,
2569
+ 64
2570
+ ],
2571
+ "dtype": "float16",
2572
+ "format": "raw",
2573
+ "nbytes": 262144,
2574
+ "byteOffset": 22028288
2575
+ },
2576
+ {
2577
+ "name": "param_207",
2578
+ "shape": [
2579
+ 11264,
2580
+ 64
2581
+ ],
2582
+ "dtype": "float16",
2583
+ "format": "raw",
2584
+ "nbytes": 1441792,
2585
+ "byteOffset": 22290432
2586
+ }
2587
+ ],
2588
+ "md5sum": "2e9b87d962f62d0b585e1762fb1ff0c8"
2589
+ },
2590
+ {
2591
+ "dataPath": "params_shard_42.bin",
2592
+ "format": "raw-shard",
2593
+ "nbytes": 23068672,
2594
+ "records": [
2595
+ {
2596
+ "name": "param_216",
2597
+ "shape": [
2598
+ 11264,
2599
+ 512
2600
+ ],
2601
+ "dtype": "uint32",
2602
+ "format": "raw",
2603
+ "nbytes": 23068672,
2604
+ "byteOffset": 0
2605
+ }
2606
+ ],
2607
+ "md5sum": "d631996e9f629ce67a13873f90b7b31f"
2608
+ },
2609
+ {
2610
+ "dataPath": "params_shard_43.bin",
2611
+ "format": "raw-shard",
2612
+ "nbytes": 23732224,
2613
+ "records": [
2614
+ {
2615
+ "name": "param_208",
2616
+ "shape": [
2617
+ 2048,
2618
+ 1408
2619
+ ],
2620
+ "dtype": "uint32",
2621
+ "format": "raw",
2622
+ "nbytes": 11534336,
2623
+ "byteOffset": 0
2624
+ },
2625
+ {
2626
+ "name": "param_209",
2627
+ "shape": [
2628
+ 2048,
2629
+ 176
2630
+ ],
2631
+ "dtype": "float16",
2632
+ "format": "raw",
2633
+ "nbytes": 720896,
2634
+ "byteOffset": 11534336
2635
+ },
2636
+ {
2637
+ "name": "param_210",
2638
+ "shape": [
2639
+ 2048
2640
+ ],
2641
+ "dtype": "float16",
2642
+ "format": "raw",
2643
+ "nbytes": 4096,
2644
+ "byteOffset": 12255232
2645
+ },
2646
+ {
2647
+ "name": "param_211",
2648
+ "shape": [
2649
+ 2048
2650
+ ],
2651
+ "dtype": "float16",
2652
+ "format": "raw",
2653
+ "nbytes": 4096,
2654
+ "byteOffset": 12259328
2655
+ },
2656
+ {
2657
+ "name": "param_212",
2658
+ "shape": [
2659
+ 2560,
2660
+ 512
2661
+ ],
2662
+ "dtype": "uint32",
2663
+ "format": "raw",
2664
+ "nbytes": 5242880,
2665
+ "byteOffset": 12263424
2666
+ },
2667
+ {
2668
+ "name": "param_213",
2669
+ "shape": [
2670
+ 2560,
2671
+ 64
2672
+ ],
2673
+ "dtype": "float16",
2674
+ "format": "raw",
2675
+ "nbytes": 327680,
2676
+ "byteOffset": 17506304
2677
+ },
2678
+ {
2679
+ "name": "param_214",
2680
+ "shape": [
2681
+ 2048,
2682
+ 512
2683
+ ],
2684
+ "dtype": "uint32",
2685
+ "format": "raw",
2686
+ "nbytes": 4194304,
2687
+ "byteOffset": 17833984
2688
+ },
2689
+ {
2690
+ "name": "param_215",
2691
+ "shape": [
2692
+ 2048,
2693
+ 64
2694
+ ],
2695
+ "dtype": "float16",
2696
+ "format": "raw",
2697
+ "nbytes": 262144,
2698
+ "byteOffset": 22028288
2699
+ },
2700
+ {
2701
+ "name": "param_217",
2702
+ "shape": [
2703
+ 11264,
2704
+ 64
2705
+ ],
2706
+ "dtype": "float16",
2707
+ "format": "raw",
2708
+ "nbytes": 1441792,
2709
+ "byteOffset": 22290432
2710
+ }
2711
+ ],
2712
+ "md5sum": "9a3c94b22fe9b4cf0b7f3a112dc93b81"
2713
+ },
2714
+ {
2715
+ "dataPath": "params_shard_44.bin",
2716
+ "format": "raw-shard",
2717
+ "nbytes": 65536000,
2718
+ "records": [
2719
+ {
2720
+ "name": "param_223",
2721
+ "shape": [
2722
+ 32000,
2723
+ 512
2724
+ ],
2725
+ "dtype": "uint32",
2726
+ "format": "raw",
2727
+ "nbytes": 65536000,
2728
+ "byteOffset": 0
2729
+ }
2730
+ ],
2731
+ "md5sum": "ac071d447c5f7e407ea30805ed610b29"
2732
+ },
2733
+ {
2734
+ "dataPath": "params_shard_45.bin",
2735
+ "format": "raw-shard",
2736
+ "nbytes": 16887808,
2737
+ "records": [
2738
+ {
2739
+ "name": "param_218",
2740
+ "shape": [
2741
+ 2048,
2742
+ 1408
2743
+ ],
2744
+ "dtype": "uint32",
2745
+ "format": "raw",
2746
+ "nbytes": 11534336,
2747
+ "byteOffset": 0
2748
+ },
2749
+ {
2750
+ "name": "param_219",
2751
+ "shape": [
2752
+ 2048,
2753
+ 176
2754
+ ],
2755
+ "dtype": "float16",
2756
+ "format": "raw",
2757
+ "nbytes": 720896,
2758
+ "byteOffset": 11534336
2759
+ },
2760
+ {
2761
+ "name": "param_220",
2762
+ "shape": [
2763
+ 2048
2764
+ ],
2765
+ "dtype": "float16",
2766
+ "format": "raw",
2767
+ "nbytes": 4096,
2768
+ "byteOffset": 12255232
2769
+ },
2770
+ {
2771
+ "name": "param_221",
2772
+ "shape": [
2773
+ 2048
2774
+ ],
2775
+ "dtype": "float16",
2776
+ "format": "raw",
2777
+ "nbytes": 4096,
2778
+ "byteOffset": 12259328
2779
+ },
2780
+ {
2781
+ "name": "param_222",
2782
+ "shape": [
2783
+ 2048
2784
+ ],
2785
+ "dtype": "float16",
2786
+ "format": "raw",
2787
+ "nbytes": 4096,
2788
+ "byteOffset": 12263424
2789
+ },
2790
+ {
2791
+ "name": "param_224",
2792
+ "shape": [
2793
+ 32000,
2794
+ 64
2795
+ ],
2796
+ "dtype": "float16",
2797
+ "format": "raw",
2798
+ "nbytes": 4096000,
2799
+ "byteOffset": 12267520
2800
+ },
2801
+ {
2802
+ "name": "param_225",
2803
+ "shape": [
2804
+ 2048,
2805
+ 64
2806
+ ],
2807
+ "dtype": "float16",
2808
+ "format": "raw",
2809
+ "nbytes": 262144,
2810
+ "byteOffset": 16363520
2811
+ },
2812
+ {
2813
+ "name": "param_226",
2814
+ "shape": [
2815
+ 2048,
2816
+ 64
2817
+ ],
2818
+ "dtype": "float16",
2819
+ "format": "raw",
2820
+ "nbytes": 262144,
2821
+ "byteOffset": 16625664
2822
+ }
2823
+ ],
2824
+ "md5sum": "7bacb82d5ec4715d028fcb47f5959ec1"
2825
+ }
2826
+ ]
2827
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232e0f500130afc33fb2ef52ba9da71982c725127b1de310bc497b5022deaffe
3
+ size 65536000
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d4f346e073996a92e9a362d65d4901ac54a1e08763d2f920d29983ccb46156
3
+ size 23068672
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338f9e458a7a930aaeed90f2d1cb8e47418bb41bf5bb5129952feea29d849944
3
+ size 23068672
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be6a5a5f008d58d49205aaa9a03d5678ffe41c5347bc37132a2f7efb42d93de8
3
+ size 23732224
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4cc46760c30b6f6df09ed3bb79408c89e0768a4bdd9e0169a2b4c67b4673fa2
3
+ size 23068672
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106e72aefb5074a2a9c8d19e3c3b0c6e9dbbc6191d8983efdf2ab7d8d4d59ad9
3
+ size 23732224
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3fb849663c71f1ddf4e1b23d3712d0073480ea53e8993e17f4e253a01e5f39b
3
+ size 23068672
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7926da7f95052b51d1e55cc2faeb9f0e28851cdc4f669f1eae22a9b75397d6
3
+ size 23732224
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77749fb025d0c79b0bb11fff166b01d46e1217c732850c92d20f50dafad0ea1d
3
+ size 23068672
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abed3fdda49b5ad47b39e3f4524cf6d00f355ee0a48515bb6489dd22f960c2e
3
+ size 23732224
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f991e2a43824a892d13dede2775be9e2d9f3d16293a0d06be8b6a29ff6f03c3
3
+ size 23068672
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3356a38f5f73bc4458867c4f1faa8c4af55bfafd3887959e603c3dcb8b35e33
3
+ size 23732224
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be958b570eaec4acbae514f61b17e146ec4cfbeb6f52da96b01f5429f14448ef
3
+ size 33398784
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4deb087e1532e4f5a706bcd57344e03e88afd093009b68af1fa99034ad8ae3
3
+ size 23068672
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c3dda714cc0611b6413e45c88604847556a0dbb2fc4419de0e02d57218dbb8
3
+ size 23732224
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b2aa9f9a039e061badd70f5c16e0e239873cbbe29f79145c89e308481b50ea
3
+ size 23068672
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b892c8b0fe7958766ae6b5183ad02f9764e6aedfdb1eb7177c18c56f4358ed27
3
+ size 23732224
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7347d62fafca9dcaf05b63d58a77426d2c7a5527edfc0b79c2255cb3e888fa66
3
+ size 23068672
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d90520a029f33eb56f42ad28fb66725a0ff9f58413a04145c43bbeff14b3c0
3
+ size 23732224
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ff80319552b39b8d611b19f0dd5e3d584d24eda35c1c28a7301d8f86d5a40d
3
+ size 23068672
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2368d6eb15d705deb500d0cc20acb52e3494475d96ac2bd2f03fbf252b7204
3
+ size 23732224
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af4639ce785317fb60fff88311fd09590d7f93af082839a32200e9081b6d89d
3
+ size 23068672
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c43bce971b6e8a89ea47d90de19cdbf5b199547b719804e97935f6ae0685c7
3
+ size 23732224
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8756d8335288e39994f886eff965b0cc5d1c494c546e8be1d7fa9291d1de85f3
3
+ size 28966912
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca54e7b182494477ed79e6b6d63f9987d113bc66041b714c5c5ffc93c2dab3f0
3
+ size 23068672
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf3f8826973bf2c90f03fb75a99c649f0071175370b3d8ba3ea0ddcce396579
3
+ size 23732224
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d961779eea39f198998ac9245bbb84af9e084daf74d47e8fffc91717ed9652
3
+ size 23068672
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2c6deb9f77cfe8c177ca8fd5a04a3b04e0ec33138774cf95f26647a352a3b8
3
+ size 23732224
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972d5b8c8abbf8f826b1cc31478899d1678520d42247845fac4396d6c88451cc
3
+ size 23068672
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80097c075f45fa79cc1a775349d4280d93e4292d350f731c9af408d802e719fd
3
+ size 23732224
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6277321e26c982bcc8184e664fdb32944a24222e89ee4efae0697ea36216442d
3
+ size 23068672
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2cf24590c03cf98b707259d694cebb9e1b5bd4b923d82d1c18ba68c39bd202
3
+ size 23732224
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be68e2b616daf62395f059b248d17930562c2a2023cbc8991b97591e47efafa0
3
+ size 23068672
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec961b2c50424e0f2c36dba85ac4f900031374ddbfc7a23b614e341fcd646677
3
+ size 23732224
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de1461fb246e348093f5b2e565179f810dad9ca6d7fae5e99de75c36e7af0f3
3
+ size 23068672
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb37ff0032eae76d1735fe792d45748257247c54a0a07454bb2ab1956d074077
3
+ size 23068672
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e42be19395b0e9c2a61a5244856fb7e99fa4ce31090967e44c3373db3df675
3
+ size 23732224
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47185762c001b0ef5f8f9df7bad3247d3647e38f501833b80ac7b06de9468ae8
3
+ size 23068672
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d246d33f6eeae389c0effacd7b4e07ee5380bbbb6569366c98c5961e20bdc3dd
3
+ size 23732224
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e9ed5184a8b8a7bee500caddbc12228a2d37cb80dc013ad51f881be89eca0da
3
+ size 65536000
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9787ff49d86675a59ad3ecb21e524ca81bd0e13439e3531a349c253aa3e6c13e
3
+ size 16887808
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a8c6f97df9fa6402f2c0679b85a9ce8eed9aadeffec94574e777e7f7fa439d9
3
+ size 23732224
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a88c8dc63b34639743805d0151e470c6d20fa22eba2273d899a51c81a743b0
3
+ size 23068672
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c67c183a359c2d2ec86ff024f4e688f4e02f6080d88f9f035d7ee2b51d5361
3
+ size 23732224
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4c4216d08f03d9378dca32cd78bf489ac6dad24f5267695e2d463f59316d9e
3
+ size 23068672
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bfd6f2c80aec1717861ecf4e741d8a7fcee820823819bcaec07456e1958cb1
3
+ size 23732224