scottto commited on
Commit
a6df218
·
1 Parent(s): fc0e349
This view is limited to 50 files because it contains too many changes.   See raw diff
TinyLlama-1.1B-Chat-v0.3-q8f16_1-android.tar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631f66652adf7095ad3d4f752b3dc25dc40aff066bae51d51229008395e719ec
3
+ size 146369
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32002,
3
+ "<|im_start|>": 32001,
4
+ "[PAD]": 32000
5
+ }
mlc-chat-config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_lib": "TinyLlama-1.1B-Chat-v0.3-q8f16_1",
3
+ "local_id": "TinyLlama-1.1B-Chat-v0.3-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": 512,
10
+ "max_window_size": 2048,
11
+ "num_shards": 1,
12
+ "shift_fill_factor": 0.3,
13
+ "tokenizer_files": [
14
+ "added_tokens.json",
15
+ "tokenizer.json",
16
+ "tokenizer.model"
17
+ ],
18
+ "model_category": "llama",
19
+ "model_name": "TinyLlama-1.1B-Chat-v0.3",
20
+ "vocab_size": 32003
21
+ }
mod_cache_before_build.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493c87fc68bad9068f02548099c10f985d1842de0aa060fd3706621e75efa29d
3
+ size 7928601
ndarray-cache.json ADDED
@@ -0,0 +1,2781 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "ParamSize": 227
4
+ },
5
+ "records": [
6
+ {
7
+ "dataPath": "params_shard_0.bin",
8
+ "format": "raw-shard",
9
+ "nbytes": 65542144,
10
+ "records": [
11
+ {
12
+ "name": "param_0",
13
+ "shape": [
14
+ 32003,
15
+ 512
16
+ ],
17
+ "dtype": "uint32",
18
+ "format": "raw",
19
+ "nbytes": 65542144,
20
+ "byteOffset": 0
21
+ }
22
+ ]
23
+ },
24
+ {
25
+ "dataPath": "params_shard_1.bin",
26
+ "format": "raw-shard",
27
+ "nbytes": 23068672,
28
+ "records": [
29
+ {
30
+ "name": "param_6",
31
+ "shape": [
32
+ 11264,
33
+ 512
34
+ ],
35
+ "dtype": "uint32",
36
+ "format": "raw",
37
+ "nbytes": 23068672,
38
+ "byteOffset": 0
39
+ }
40
+ ]
41
+ },
42
+ {
43
+ "dataPath": "params_shard_2.bin",
44
+ "format": "raw-shard",
45
+ "nbytes": 33399168,
46
+ "records": [
47
+ {
48
+ "name": "param_1",
49
+ "shape": [
50
+ 32003,
51
+ 64
52
+ ],
53
+ "dtype": "float16",
54
+ "format": "raw",
55
+ "nbytes": 4096384,
56
+ "byteOffset": 0
57
+ },
58
+ {
59
+ "name": "param_2",
60
+ "shape": [
61
+ 2560,
62
+ 512
63
+ ],
64
+ "dtype": "uint32",
65
+ "format": "raw",
66
+ "nbytes": 5242880,
67
+ "byteOffset": 4096384
68
+ },
69
+ {
70
+ "name": "param_3",
71
+ "shape": [
72
+ 2560,
73
+ 64
74
+ ],
75
+ "dtype": "float16",
76
+ "format": "raw",
77
+ "nbytes": 327680,
78
+ "byteOffset": 9339264
79
+ },
80
+ {
81
+ "name": "param_4",
82
+ "shape": [
83
+ 2048,
84
+ 512
85
+ ],
86
+ "dtype": "uint32",
87
+ "format": "raw",
88
+ "nbytes": 4194304,
89
+ "byteOffset": 9666944
90
+ },
91
+ {
92
+ "name": "param_5",
93
+ "shape": [
94
+ 2048,
95
+ 64
96
+ ],
97
+ "dtype": "float16",
98
+ "format": "raw",
99
+ "nbytes": 262144,
100
+ "byteOffset": 13861248
101
+ },
102
+ {
103
+ "name": "param_7",
104
+ "shape": [
105
+ 11264,
106
+ 64
107
+ ],
108
+ "dtype": "float16",
109
+ "format": "raw",
110
+ "nbytes": 1441792,
111
+ "byteOffset": 14123392
112
+ },
113
+ {
114
+ "name": "param_8",
115
+ "shape": [
116
+ 2048,
117
+ 1408
118
+ ],
119
+ "dtype": "uint32",
120
+ "format": "raw",
121
+ "nbytes": 11534336,
122
+ "byteOffset": 15565184
123
+ },
124
+ {
125
+ "name": "param_9",
126
+ "shape": [
127
+ 2048,
128
+ 176
129
+ ],
130
+ "dtype": "float16",
131
+ "format": "raw",
132
+ "nbytes": 720896,
133
+ "byteOffset": 27099520
134
+ },
135
+ {
136
+ "name": "param_10",
137
+ "shape": [
138
+ 2048
139
+ ],
140
+ "dtype": "float16",
141
+ "format": "raw",
142
+ "nbytes": 4096,
143
+ "byteOffset": 27820416
144
+ },
145
+ {
146
+ "name": "param_11",
147
+ "shape": [
148
+ 2048
149
+ ],
150
+ "dtype": "float16",
151
+ "format": "raw",
152
+ "nbytes": 4096,
153
+ "byteOffset": 27824512
154
+ },
155
+ {
156
+ "name": "param_12",
157
+ "shape": [
158
+ 2560,
159
+ 512
160
+ ],
161
+ "dtype": "uint32",
162
+ "format": "raw",
163
+ "nbytes": 5242880,
164
+ "byteOffset": 27828608
165
+ },
166
+ {
167
+ "name": "param_13",
168
+ "shape": [
169
+ 2560,
170
+ 64
171
+ ],
172
+ "dtype": "float16",
173
+ "format": "raw",
174
+ "nbytes": 327680,
175
+ "byteOffset": 33071488
176
+ }
177
+ ]
178
+ },
179
+ {
180
+ "dataPath": "params_shard_3.bin",
181
+ "format": "raw-shard",
182
+ "nbytes": 28966912,
183
+ "records": [
184
+ {
185
+ "name": "param_14",
186
+ "shape": [
187
+ 2048,
188
+ 512
189
+ ],
190
+ "dtype": "uint32",
191
+ "format": "raw",
192
+ "nbytes": 4194304,
193
+ "byteOffset": 0
194
+ },
195
+ {
196
+ "name": "param_15",
197
+ "shape": [
198
+ 2048,
199
+ 64
200
+ ],
201
+ "dtype": "float16",
202
+ "format": "raw",
203
+ "nbytes": 262144,
204
+ "byteOffset": 4194304
205
+ },
206
+ {
207
+ "name": "param_16",
208
+ "shape": [
209
+ 11264,
210
+ 512
211
+ ],
212
+ "dtype": "uint32",
213
+ "format": "raw",
214
+ "nbytes": 23068672,
215
+ "byteOffset": 4456448
216
+ },
217
+ {
218
+ "name": "param_17",
219
+ "shape": [
220
+ 11264,
221
+ 64
222
+ ],
223
+ "dtype": "float16",
224
+ "format": "raw",
225
+ "nbytes": 1441792,
226
+ "byteOffset": 27525120
227
+ }
228
+ ]
229
+ },
230
+ {
231
+ "dataPath": "params_shard_4.bin",
232
+ "format": "raw-shard",
233
+ "nbytes": 23068672,
234
+ "records": [
235
+ {
236
+ "name": "param_26",
237
+ "shape": [
238
+ 11264,
239
+ 512
240
+ ],
241
+ "dtype": "uint32",
242
+ "format": "raw",
243
+ "nbytes": 23068672,
244
+ "byteOffset": 0
245
+ }
246
+ ]
247
+ },
248
+ {
249
+ "dataPath": "params_shard_5.bin",
250
+ "format": "raw-shard",
251
+ "nbytes": 23732224,
252
+ "records": [
253
+ {
254
+ "name": "param_18",
255
+ "shape": [
256
+ 2048,
257
+ 1408
258
+ ],
259
+ "dtype": "uint32",
260
+ "format": "raw",
261
+ "nbytes": 11534336,
262
+ "byteOffset": 0
263
+ },
264
+ {
265
+ "name": "param_19",
266
+ "shape": [
267
+ 2048,
268
+ 176
269
+ ],
270
+ "dtype": "float16",
271
+ "format": "raw",
272
+ "nbytes": 720896,
273
+ "byteOffset": 11534336
274
+ },
275
+ {
276
+ "name": "param_20",
277
+ "shape": [
278
+ 2048
279
+ ],
280
+ "dtype": "float16",
281
+ "format": "raw",
282
+ "nbytes": 4096,
283
+ "byteOffset": 12255232
284
+ },
285
+ {
286
+ "name": "param_21",
287
+ "shape": [
288
+ 2048
289
+ ],
290
+ "dtype": "float16",
291
+ "format": "raw",
292
+ "nbytes": 4096,
293
+ "byteOffset": 12259328
294
+ },
295
+ {
296
+ "name": "param_22",
297
+ "shape": [
298
+ 2560,
299
+ 512
300
+ ],
301
+ "dtype": "uint32",
302
+ "format": "raw",
303
+ "nbytes": 5242880,
304
+ "byteOffset": 12263424
305
+ },
306
+ {
307
+ "name": "param_23",
308
+ "shape": [
309
+ 2560,
310
+ 64
311
+ ],
312
+ "dtype": "float16",
313
+ "format": "raw",
314
+ "nbytes": 327680,
315
+ "byteOffset": 17506304
316
+ },
317
+ {
318
+ "name": "param_24",
319
+ "shape": [
320
+ 2048,
321
+ 512
322
+ ],
323
+ "dtype": "uint32",
324
+ "format": "raw",
325
+ "nbytes": 4194304,
326
+ "byteOffset": 17833984
327
+ },
328
+ {
329
+ "name": "param_25",
330
+ "shape": [
331
+ 2048,
332
+ 64
333
+ ],
334
+ "dtype": "float16",
335
+ "format": "raw",
336
+ "nbytes": 262144,
337
+ "byteOffset": 22028288
338
+ },
339
+ {
340
+ "name": "param_27",
341
+ "shape": [
342
+ 11264,
343
+ 64
344
+ ],
345
+ "dtype": "float16",
346
+ "format": "raw",
347
+ "nbytes": 1441792,
348
+ "byteOffset": 22290432
349
+ }
350
+ ]
351
+ },
352
+ {
353
+ "dataPath": "params_shard_6.bin",
354
+ "format": "raw-shard",
355
+ "nbytes": 23068672,
356
+ "records": [
357
+ {
358
+ "name": "param_36",
359
+ "shape": [
360
+ 11264,
361
+ 512
362
+ ],
363
+ "dtype": "uint32",
364
+ "format": "raw",
365
+ "nbytes": 23068672,
366
+ "byteOffset": 0
367
+ }
368
+ ]
369
+ },
370
+ {
371
+ "dataPath": "params_shard_7.bin",
372
+ "format": "raw-shard",
373
+ "nbytes": 23732224,
374
+ "records": [
375
+ {
376
+ "name": "param_28",
377
+ "shape": [
378
+ 2048,
379
+ 1408
380
+ ],
381
+ "dtype": "uint32",
382
+ "format": "raw",
383
+ "nbytes": 11534336,
384
+ "byteOffset": 0
385
+ },
386
+ {
387
+ "name": "param_29",
388
+ "shape": [
389
+ 2048,
390
+ 176
391
+ ],
392
+ "dtype": "float16",
393
+ "format": "raw",
394
+ "nbytes": 720896,
395
+ "byteOffset": 11534336
396
+ },
397
+ {
398
+ "name": "param_30",
399
+ "shape": [
400
+ 2048
401
+ ],
402
+ "dtype": "float16",
403
+ "format": "raw",
404
+ "nbytes": 4096,
405
+ "byteOffset": 12255232
406
+ },
407
+ {
408
+ "name": "param_31",
409
+ "shape": [
410
+ 2048
411
+ ],
412
+ "dtype": "float16",
413
+ "format": "raw",
414
+ "nbytes": 4096,
415
+ "byteOffset": 12259328
416
+ },
417
+ {
418
+ "name": "param_32",
419
+ "shape": [
420
+ 2560,
421
+ 512
422
+ ],
423
+ "dtype": "uint32",
424
+ "format": "raw",
425
+ "nbytes": 5242880,
426
+ "byteOffset": 12263424
427
+ },
428
+ {
429
+ "name": "param_33",
430
+ "shape": [
431
+ 2560,
432
+ 64
433
+ ],
434
+ "dtype": "float16",
435
+ "format": "raw",
436
+ "nbytes": 327680,
437
+ "byteOffset": 17506304
438
+ },
439
+ {
440
+ "name": "param_34",
441
+ "shape": [
442
+ 2048,
443
+ 512
444
+ ],
445
+ "dtype": "uint32",
446
+ "format": "raw",
447
+ "nbytes": 4194304,
448
+ "byteOffset": 17833984
449
+ },
450
+ {
451
+ "name": "param_35",
452
+ "shape": [
453
+ 2048,
454
+ 64
455
+ ],
456
+ "dtype": "float16",
457
+ "format": "raw",
458
+ "nbytes": 262144,
459
+ "byteOffset": 22028288
460
+ },
461
+ {
462
+ "name": "param_37",
463
+ "shape": [
464
+ 11264,
465
+ 64
466
+ ],
467
+ "dtype": "float16",
468
+ "format": "raw",
469
+ "nbytes": 1441792,
470
+ "byteOffset": 22290432
471
+ }
472
+ ]
473
+ },
474
+ {
475
+ "dataPath": "params_shard_8.bin",
476
+ "format": "raw-shard",
477
+ "nbytes": 23068672,
478
+ "records": [
479
+ {
480
+ "name": "param_46",
481
+ "shape": [
482
+ 11264,
483
+ 512
484
+ ],
485
+ "dtype": "uint32",
486
+ "format": "raw",
487
+ "nbytes": 23068672,
488
+ "byteOffset": 0
489
+ }
490
+ ]
491
+ },
492
+ {
493
+ "dataPath": "params_shard_9.bin",
494
+ "format": "raw-shard",
495
+ "nbytes": 23732224,
496
+ "records": [
497
+ {
498
+ "name": "param_38",
499
+ "shape": [
500
+ 2048,
501
+ 1408
502
+ ],
503
+ "dtype": "uint32",
504
+ "format": "raw",
505
+ "nbytes": 11534336,
506
+ "byteOffset": 0
507
+ },
508
+ {
509
+ "name": "param_39",
510
+ "shape": [
511
+ 2048,
512
+ 176
513
+ ],
514
+ "dtype": "float16",
515
+ "format": "raw",
516
+ "nbytes": 720896,
517
+ "byteOffset": 11534336
518
+ },
519
+ {
520
+ "name": "param_40",
521
+ "shape": [
522
+ 2048
523
+ ],
524
+ "dtype": "float16",
525
+ "format": "raw",
526
+ "nbytes": 4096,
527
+ "byteOffset": 12255232
528
+ },
529
+ {
530
+ "name": "param_41",
531
+ "shape": [
532
+ 2048
533
+ ],
534
+ "dtype": "float16",
535
+ "format": "raw",
536
+ "nbytes": 4096,
537
+ "byteOffset": 12259328
538
+ },
539
+ {
540
+ "name": "param_42",
541
+ "shape": [
542
+ 2560,
543
+ 512
544
+ ],
545
+ "dtype": "uint32",
546
+ "format": "raw",
547
+ "nbytes": 5242880,
548
+ "byteOffset": 12263424
549
+ },
550
+ {
551
+ "name": "param_43",
552
+ "shape": [
553
+ 2560,
554
+ 64
555
+ ],
556
+ "dtype": "float16",
557
+ "format": "raw",
558
+ "nbytes": 327680,
559
+ "byteOffset": 17506304
560
+ },
561
+ {
562
+ "name": "param_44",
563
+ "shape": [
564
+ 2048,
565
+ 512
566
+ ],
567
+ "dtype": "uint32",
568
+ "format": "raw",
569
+ "nbytes": 4194304,
570
+ "byteOffset": 17833984
571
+ },
572
+ {
573
+ "name": "param_45",
574
+ "shape": [
575
+ 2048,
576
+ 64
577
+ ],
578
+ "dtype": "float16",
579
+ "format": "raw",
580
+ "nbytes": 262144,
581
+ "byteOffset": 22028288
582
+ },
583
+ {
584
+ "name": "param_47",
585
+ "shape": [
586
+ 11264,
587
+ 64
588
+ ],
589
+ "dtype": "float16",
590
+ "format": "raw",
591
+ "nbytes": 1441792,
592
+ "byteOffset": 22290432
593
+ }
594
+ ]
595
+ },
596
+ {
597
+ "dataPath": "params_shard_10.bin",
598
+ "format": "raw-shard",
599
+ "nbytes": 23068672,
600
+ "records": [
601
+ {
602
+ "name": "param_56",
603
+ "shape": [
604
+ 11264,
605
+ 512
606
+ ],
607
+ "dtype": "uint32",
608
+ "format": "raw",
609
+ "nbytes": 23068672,
610
+ "byteOffset": 0
611
+ }
612
+ ]
613
+ },
614
+ {
615
+ "dataPath": "params_shard_11.bin",
616
+ "format": "raw-shard",
617
+ "nbytes": 23732224,
618
+ "records": [
619
+ {
620
+ "name": "param_48",
621
+ "shape": [
622
+ 2048,
623
+ 1408
624
+ ],
625
+ "dtype": "uint32",
626
+ "format": "raw",
627
+ "nbytes": 11534336,
628
+ "byteOffset": 0
629
+ },
630
+ {
631
+ "name": "param_49",
632
+ "shape": [
633
+ 2048,
634
+ 176
635
+ ],
636
+ "dtype": "float16",
637
+ "format": "raw",
638
+ "nbytes": 720896,
639
+ "byteOffset": 11534336
640
+ },
641
+ {
642
+ "name": "param_50",
643
+ "shape": [
644
+ 2048
645
+ ],
646
+ "dtype": "float16",
647
+ "format": "raw",
648
+ "nbytes": 4096,
649
+ "byteOffset": 12255232
650
+ },
651
+ {
652
+ "name": "param_51",
653
+ "shape": [
654
+ 2048
655
+ ],
656
+ "dtype": "float16",
657
+ "format": "raw",
658
+ "nbytes": 4096,
659
+ "byteOffset": 12259328
660
+ },
661
+ {
662
+ "name": "param_52",
663
+ "shape": [
664
+ 2560,
665
+ 512
666
+ ],
667
+ "dtype": "uint32",
668
+ "format": "raw",
669
+ "nbytes": 5242880,
670
+ "byteOffset": 12263424
671
+ },
672
+ {
673
+ "name": "param_53",
674
+ "shape": [
675
+ 2560,
676
+ 64
677
+ ],
678
+ "dtype": "float16",
679
+ "format": "raw",
680
+ "nbytes": 327680,
681
+ "byteOffset": 17506304
682
+ },
683
+ {
684
+ "name": "param_54",
685
+ "shape": [
686
+ 2048,
687
+ 512
688
+ ],
689
+ "dtype": "uint32",
690
+ "format": "raw",
691
+ "nbytes": 4194304,
692
+ "byteOffset": 17833984
693
+ },
694
+ {
695
+ "name": "param_55",
696
+ "shape": [
697
+ 2048,
698
+ 64
699
+ ],
700
+ "dtype": "float16",
701
+ "format": "raw",
702
+ "nbytes": 262144,
703
+ "byteOffset": 22028288
704
+ },
705
+ {
706
+ "name": "param_57",
707
+ "shape": [
708
+ 11264,
709
+ 64
710
+ ],
711
+ "dtype": "float16",
712
+ "format": "raw",
713
+ "nbytes": 1441792,
714
+ "byteOffset": 22290432
715
+ }
716
+ ]
717
+ },
718
+ {
719
+ "dataPath": "params_shard_12.bin",
720
+ "format": "raw-shard",
721
+ "nbytes": 23068672,
722
+ "records": [
723
+ {
724
+ "name": "param_66",
725
+ "shape": [
726
+ 11264,
727
+ 512
728
+ ],
729
+ "dtype": "uint32",
730
+ "format": "raw",
731
+ "nbytes": 23068672,
732
+ "byteOffset": 0
733
+ }
734
+ ]
735
+ },
736
+ {
737
+ "dataPath": "params_shard_13.bin",
738
+ "format": "raw-shard",
739
+ "nbytes": 23732224,
740
+ "records": [
741
+ {
742
+ "name": "param_58",
743
+ "shape": [
744
+ 2048,
745
+ 1408
746
+ ],
747
+ "dtype": "uint32",
748
+ "format": "raw",
749
+ "nbytes": 11534336,
750
+ "byteOffset": 0
751
+ },
752
+ {
753
+ "name": "param_59",
754
+ "shape": [
755
+ 2048,
756
+ 176
757
+ ],
758
+ "dtype": "float16",
759
+ "format": "raw",
760
+ "nbytes": 720896,
761
+ "byteOffset": 11534336
762
+ },
763
+ {
764
+ "name": "param_60",
765
+ "shape": [
766
+ 2048
767
+ ],
768
+ "dtype": "float16",
769
+ "format": "raw",
770
+ "nbytes": 4096,
771
+ "byteOffset": 12255232
772
+ },
773
+ {
774
+ "name": "param_61",
775
+ "shape": [
776
+ 2048
777
+ ],
778
+ "dtype": "float16",
779
+ "format": "raw",
780
+ "nbytes": 4096,
781
+ "byteOffset": 12259328
782
+ },
783
+ {
784
+ "name": "param_62",
785
+ "shape": [
786
+ 2560,
787
+ 512
788
+ ],
789
+ "dtype": "uint32",
790
+ "format": "raw",
791
+ "nbytes": 5242880,
792
+ "byteOffset": 12263424
793
+ },
794
+ {
795
+ "name": "param_63",
796
+ "shape": [
797
+ 2560,
798
+ 64
799
+ ],
800
+ "dtype": "float16",
801
+ "format": "raw",
802
+ "nbytes": 327680,
803
+ "byteOffset": 17506304
804
+ },
805
+ {
806
+ "name": "param_64",
807
+ "shape": [
808
+ 2048,
809
+ 512
810
+ ],
811
+ "dtype": "uint32",
812
+ "format": "raw",
813
+ "nbytes": 4194304,
814
+ "byteOffset": 17833984
815
+ },
816
+ {
817
+ "name": "param_65",
818
+ "shape": [
819
+ 2048,
820
+ 64
821
+ ],
822
+ "dtype": "float16",
823
+ "format": "raw",
824
+ "nbytes": 262144,
825
+ "byteOffset": 22028288
826
+ },
827
+ {
828
+ "name": "param_67",
829
+ "shape": [
830
+ 11264,
831
+ 64
832
+ ],
833
+ "dtype": "float16",
834
+ "format": "raw",
835
+ "nbytes": 1441792,
836
+ "byteOffset": 22290432
837
+ }
838
+ ]
839
+ },
840
+ {
841
+ "dataPath": "params_shard_14.bin",
842
+ "format": "raw-shard",
843
+ "nbytes": 23068672,
844
+ "records": [
845
+ {
846
+ "name": "param_76",
847
+ "shape": [
848
+ 11264,
849
+ 512
850
+ ],
851
+ "dtype": "uint32",
852
+ "format": "raw",
853
+ "nbytes": 23068672,
854
+ "byteOffset": 0
855
+ }
856
+ ]
857
+ },
858
+ {
859
+ "dataPath": "params_shard_15.bin",
860
+ "format": "raw-shard",
861
+ "nbytes": 23732224,
862
+ "records": [
863
+ {
864
+ "name": "param_68",
865
+ "shape": [
866
+ 2048,
867
+ 1408
868
+ ],
869
+ "dtype": "uint32",
870
+ "format": "raw",
871
+ "nbytes": 11534336,
872
+ "byteOffset": 0
873
+ },
874
+ {
875
+ "name": "param_69",
876
+ "shape": [
877
+ 2048,
878
+ 176
879
+ ],
880
+ "dtype": "float16",
881
+ "format": "raw",
882
+ "nbytes": 720896,
883
+ "byteOffset": 11534336
884
+ },
885
+ {
886
+ "name": "param_70",
887
+ "shape": [
888
+ 2048
889
+ ],
890
+ "dtype": "float16",
891
+ "format": "raw",
892
+ "nbytes": 4096,
893
+ "byteOffset": 12255232
894
+ },
895
+ {
896
+ "name": "param_71",
897
+ "shape": [
898
+ 2048
899
+ ],
900
+ "dtype": "float16",
901
+ "format": "raw",
902
+ "nbytes": 4096,
903
+ "byteOffset": 12259328
904
+ },
905
+ {
906
+ "name": "param_72",
907
+ "shape": [
908
+ 2560,
909
+ 512
910
+ ],
911
+ "dtype": "uint32",
912
+ "format": "raw",
913
+ "nbytes": 5242880,
914
+ "byteOffset": 12263424
915
+ },
916
+ {
917
+ "name": "param_73",
918
+ "shape": [
919
+ 2560,
920
+ 64
921
+ ],
922
+ "dtype": "float16",
923
+ "format": "raw",
924
+ "nbytes": 327680,
925
+ "byteOffset": 17506304
926
+ },
927
+ {
928
+ "name": "param_74",
929
+ "shape": [
930
+ 2048,
931
+ 512
932
+ ],
933
+ "dtype": "uint32",
934
+ "format": "raw",
935
+ "nbytes": 4194304,
936
+ "byteOffset": 17833984
937
+ },
938
+ {
939
+ "name": "param_75",
940
+ "shape": [
941
+ 2048,
942
+ 64
943
+ ],
944
+ "dtype": "float16",
945
+ "format": "raw",
946
+ "nbytes": 262144,
947
+ "byteOffset": 22028288
948
+ },
949
+ {
950
+ "name": "param_77",
951
+ "shape": [
952
+ 11264,
953
+ 64
954
+ ],
955
+ "dtype": "float16",
956
+ "format": "raw",
957
+ "nbytes": 1441792,
958
+ "byteOffset": 22290432
959
+ }
960
+ ]
961
+ },
962
+ {
963
+ "dataPath": "params_shard_16.bin",
964
+ "format": "raw-shard",
965
+ "nbytes": 23068672,
966
+ "records": [
967
+ {
968
+ "name": "param_86",
969
+ "shape": [
970
+ 11264,
971
+ 512
972
+ ],
973
+ "dtype": "uint32",
974
+ "format": "raw",
975
+ "nbytes": 23068672,
976
+ "byteOffset": 0
977
+ }
978
+ ]
979
+ },
980
+ {
981
+ "dataPath": "params_shard_17.bin",
982
+ "format": "raw-shard",
983
+ "nbytes": 23732224,
984
+ "records": [
985
+ {
986
+ "name": "param_78",
987
+ "shape": [
988
+ 2048,
989
+ 1408
990
+ ],
991
+ "dtype": "uint32",
992
+ "format": "raw",
993
+ "nbytes": 11534336,
994
+ "byteOffset": 0
995
+ },
996
+ {
997
+ "name": "param_79",
998
+ "shape": [
999
+ 2048,
1000
+ 176
1001
+ ],
1002
+ "dtype": "float16",
1003
+ "format": "raw",
1004
+ "nbytes": 720896,
1005
+ "byteOffset": 11534336
1006
+ },
1007
+ {
1008
+ "name": "param_80",
1009
+ "shape": [
1010
+ 2048
1011
+ ],
1012
+ "dtype": "float16",
1013
+ "format": "raw",
1014
+ "nbytes": 4096,
1015
+ "byteOffset": 12255232
1016
+ },
1017
+ {
1018
+ "name": "param_81",
1019
+ "shape": [
1020
+ 2048
1021
+ ],
1022
+ "dtype": "float16",
1023
+ "format": "raw",
1024
+ "nbytes": 4096,
1025
+ "byteOffset": 12259328
1026
+ },
1027
+ {
1028
+ "name": "param_82",
1029
+ "shape": [
1030
+ 2560,
1031
+ 512
1032
+ ],
1033
+ "dtype": "uint32",
1034
+ "format": "raw",
1035
+ "nbytes": 5242880,
1036
+ "byteOffset": 12263424
1037
+ },
1038
+ {
1039
+ "name": "param_83",
1040
+ "shape": [
1041
+ 2560,
1042
+ 64
1043
+ ],
1044
+ "dtype": "float16",
1045
+ "format": "raw",
1046
+ "nbytes": 327680,
1047
+ "byteOffset": 17506304
1048
+ },
1049
+ {
1050
+ "name": "param_84",
1051
+ "shape": [
1052
+ 2048,
1053
+ 512
1054
+ ],
1055
+ "dtype": "uint32",
1056
+ "format": "raw",
1057
+ "nbytes": 4194304,
1058
+ "byteOffset": 17833984
1059
+ },
1060
+ {
1061
+ "name": "param_85",
1062
+ "shape": [
1063
+ 2048,
1064
+ 64
1065
+ ],
1066
+ "dtype": "float16",
1067
+ "format": "raw",
1068
+ "nbytes": 262144,
1069
+ "byteOffset": 22028288
1070
+ },
1071
+ {
1072
+ "name": "param_87",
1073
+ "shape": [
1074
+ 11264,
1075
+ 64
1076
+ ],
1077
+ "dtype": "float16",
1078
+ "format": "raw",
1079
+ "nbytes": 1441792,
1080
+ "byteOffset": 22290432
1081
+ }
1082
+ ]
1083
+ },
1084
+ {
1085
+ "dataPath": "params_shard_18.bin",
1086
+ "format": "raw-shard",
1087
+ "nbytes": 23068672,
1088
+ "records": [
1089
+ {
1090
+ "name": "param_96",
1091
+ "shape": [
1092
+ 11264,
1093
+ 512
1094
+ ],
1095
+ "dtype": "uint32",
1096
+ "format": "raw",
1097
+ "nbytes": 23068672,
1098
+ "byteOffset": 0
1099
+ }
1100
+ ]
1101
+ },
1102
+ {
1103
+ "dataPath": "params_shard_19.bin",
1104
+ "format": "raw-shard",
1105
+ "nbytes": 23732224,
1106
+ "records": [
1107
+ {
1108
+ "name": "param_88",
1109
+ "shape": [
1110
+ 2048,
1111
+ 1408
1112
+ ],
1113
+ "dtype": "uint32",
1114
+ "format": "raw",
1115
+ "nbytes": 11534336,
1116
+ "byteOffset": 0
1117
+ },
1118
+ {
1119
+ "name": "param_89",
1120
+ "shape": [
1121
+ 2048,
1122
+ 176
1123
+ ],
1124
+ "dtype": "float16",
1125
+ "format": "raw",
1126
+ "nbytes": 720896,
1127
+ "byteOffset": 11534336
1128
+ },
1129
+ {
1130
+ "name": "param_90",
1131
+ "shape": [
1132
+ 2048
1133
+ ],
1134
+ "dtype": "float16",
1135
+ "format": "raw",
1136
+ "nbytes": 4096,
1137
+ "byteOffset": 12255232
1138
+ },
1139
+ {
1140
+ "name": "param_91",
1141
+ "shape": [
1142
+ 2048
1143
+ ],
1144
+ "dtype": "float16",
1145
+ "format": "raw",
1146
+ "nbytes": 4096,
1147
+ "byteOffset": 12259328
1148
+ },
1149
+ {
1150
+ "name": "param_92",
1151
+ "shape": [
1152
+ 2560,
1153
+ 512
1154
+ ],
1155
+ "dtype": "uint32",
1156
+ "format": "raw",
1157
+ "nbytes": 5242880,
1158
+ "byteOffset": 12263424
1159
+ },
1160
+ {
1161
+ "name": "param_93",
1162
+ "shape": [
1163
+ 2560,
1164
+ 64
1165
+ ],
1166
+ "dtype": "float16",
1167
+ "format": "raw",
1168
+ "nbytes": 327680,
1169
+ "byteOffset": 17506304
1170
+ },
1171
+ {
1172
+ "name": "param_94",
1173
+ "shape": [
1174
+ 2048,
1175
+ 512
1176
+ ],
1177
+ "dtype": "uint32",
1178
+ "format": "raw",
1179
+ "nbytes": 4194304,
1180
+ "byteOffset": 17833984
1181
+ },
1182
+ {
1183
+ "name": "param_95",
1184
+ "shape": [
1185
+ 2048,
1186
+ 64
1187
+ ],
1188
+ "dtype": "float16",
1189
+ "format": "raw",
1190
+ "nbytes": 262144,
1191
+ "byteOffset": 22028288
1192
+ },
1193
+ {
1194
+ "name": "param_97",
1195
+ "shape": [
1196
+ 11264,
1197
+ 64
1198
+ ],
1199
+ "dtype": "float16",
1200
+ "format": "raw",
1201
+ "nbytes": 1441792,
1202
+ "byteOffset": 22290432
1203
+ }
1204
+ ]
1205
+ },
1206
+ {
1207
+ "dataPath": "params_shard_20.bin",
1208
+ "format": "raw-shard",
1209
+ "nbytes": 23068672,
1210
+ "records": [
1211
+ {
1212
+ "name": "param_106",
1213
+ "shape": [
1214
+ 11264,
1215
+ 512
1216
+ ],
1217
+ "dtype": "uint32",
1218
+ "format": "raw",
1219
+ "nbytes": 23068672,
1220
+ "byteOffset": 0
1221
+ }
1222
+ ]
1223
+ },
1224
+ {
1225
+ "dataPath": "params_shard_21.bin",
1226
+ "format": "raw-shard",
1227
+ "nbytes": 23732224,
1228
+ "records": [
1229
+ {
1230
+ "name": "param_98",
1231
+ "shape": [
1232
+ 2048,
1233
+ 1408
1234
+ ],
1235
+ "dtype": "uint32",
1236
+ "format": "raw",
1237
+ "nbytes": 11534336,
1238
+ "byteOffset": 0
1239
+ },
1240
+ {
1241
+ "name": "param_99",
1242
+ "shape": [
1243
+ 2048,
1244
+ 176
1245
+ ],
1246
+ "dtype": "float16",
1247
+ "format": "raw",
1248
+ "nbytes": 720896,
1249
+ "byteOffset": 11534336
1250
+ },
1251
+ {
1252
+ "name": "param_100",
1253
+ "shape": [
1254
+ 2048
1255
+ ],
1256
+ "dtype": "float16",
1257
+ "format": "raw",
1258
+ "nbytes": 4096,
1259
+ "byteOffset": 12255232
1260
+ },
1261
+ {
1262
+ "name": "param_101",
1263
+ "shape": [
1264
+ 2048
1265
+ ],
1266
+ "dtype": "float16",
1267
+ "format": "raw",
1268
+ "nbytes": 4096,
1269
+ "byteOffset": 12259328
1270
+ },
1271
+ {
1272
+ "name": "param_102",
1273
+ "shape": [
1274
+ 2560,
1275
+ 512
1276
+ ],
1277
+ "dtype": "uint32",
1278
+ "format": "raw",
1279
+ "nbytes": 5242880,
1280
+ "byteOffset": 12263424
1281
+ },
1282
+ {
1283
+ "name": "param_103",
1284
+ "shape": [
1285
+ 2560,
1286
+ 64
1287
+ ],
1288
+ "dtype": "float16",
1289
+ "format": "raw",
1290
+ "nbytes": 327680,
1291
+ "byteOffset": 17506304
1292
+ },
1293
+ {
1294
+ "name": "param_104",
1295
+ "shape": [
1296
+ 2048,
1297
+ 512
1298
+ ],
1299
+ "dtype": "uint32",
1300
+ "format": "raw",
1301
+ "nbytes": 4194304,
1302
+ "byteOffset": 17833984
1303
+ },
1304
+ {
1305
+ "name": "param_105",
1306
+ "shape": [
1307
+ 2048,
1308
+ 64
1309
+ ],
1310
+ "dtype": "float16",
1311
+ "format": "raw",
1312
+ "nbytes": 262144,
1313
+ "byteOffset": 22028288
1314
+ },
1315
+ {
1316
+ "name": "param_107",
1317
+ "shape": [
1318
+ 11264,
1319
+ 64
1320
+ ],
1321
+ "dtype": "float16",
1322
+ "format": "raw",
1323
+ "nbytes": 1441792,
1324
+ "byteOffset": 22290432
1325
+ }
1326
+ ]
1327
+ },
1328
+ {
1329
+ "dataPath": "params_shard_22.bin",
1330
+ "format": "raw-shard",
1331
+ "nbytes": 23068672,
1332
+ "records": [
1333
+ {
1334
+ "name": "param_116",
1335
+ "shape": [
1336
+ 11264,
1337
+ 512
1338
+ ],
1339
+ "dtype": "uint32",
1340
+ "format": "raw",
1341
+ "nbytes": 23068672,
1342
+ "byteOffset": 0
1343
+ }
1344
+ ]
1345
+ },
1346
+ {
1347
+ "dataPath": "params_shard_23.bin",
1348
+ "format": "raw-shard",
1349
+ "nbytes": 23732224,
1350
+ "records": [
1351
+ {
1352
+ "name": "param_108",
1353
+ "shape": [
1354
+ 2048,
1355
+ 1408
1356
+ ],
1357
+ "dtype": "uint32",
1358
+ "format": "raw",
1359
+ "nbytes": 11534336,
1360
+ "byteOffset": 0
1361
+ },
1362
+ {
1363
+ "name": "param_109",
1364
+ "shape": [
1365
+ 2048,
1366
+ 176
1367
+ ],
1368
+ "dtype": "float16",
1369
+ "format": "raw",
1370
+ "nbytes": 720896,
1371
+ "byteOffset": 11534336
1372
+ },
1373
+ {
1374
+ "name": "param_110",
1375
+ "shape": [
1376
+ 2048
1377
+ ],
1378
+ "dtype": "float16",
1379
+ "format": "raw",
1380
+ "nbytes": 4096,
1381
+ "byteOffset": 12255232
1382
+ },
1383
+ {
1384
+ "name": "param_111",
1385
+ "shape": [
1386
+ 2048
1387
+ ],
1388
+ "dtype": "float16",
1389
+ "format": "raw",
1390
+ "nbytes": 4096,
1391
+ "byteOffset": 12259328
1392
+ },
1393
+ {
1394
+ "name": "param_112",
1395
+ "shape": [
1396
+ 2560,
1397
+ 512
1398
+ ],
1399
+ "dtype": "uint32",
1400
+ "format": "raw",
1401
+ "nbytes": 5242880,
1402
+ "byteOffset": 12263424
1403
+ },
1404
+ {
1405
+ "name": "param_113",
1406
+ "shape": [
1407
+ 2560,
1408
+ 64
1409
+ ],
1410
+ "dtype": "float16",
1411
+ "format": "raw",
1412
+ "nbytes": 327680,
1413
+ "byteOffset": 17506304
1414
+ },
1415
+ {
1416
+ "name": "param_114",
1417
+ "shape": [
1418
+ 2048,
1419
+ 512
1420
+ ],
1421
+ "dtype": "uint32",
1422
+ "format": "raw",
1423
+ "nbytes": 4194304,
1424
+ "byteOffset": 17833984
1425
+ },
1426
+ {
1427
+ "name": "param_115",
1428
+ "shape": [
1429
+ 2048,
1430
+ 64
1431
+ ],
1432
+ "dtype": "float16",
1433
+ "format": "raw",
1434
+ "nbytes": 262144,
1435
+ "byteOffset": 22028288
1436
+ },
1437
+ {
1438
+ "name": "param_117",
1439
+ "shape": [
1440
+ 11264,
1441
+ 64
1442
+ ],
1443
+ "dtype": "float16",
1444
+ "format": "raw",
1445
+ "nbytes": 1441792,
1446
+ "byteOffset": 22290432
1447
+ }
1448
+ ]
1449
+ },
1450
+ {
1451
+ "dataPath": "params_shard_24.bin",
1452
+ "format": "raw-shard",
1453
+ "nbytes": 23068672,
1454
+ "records": [
1455
+ {
1456
+ "name": "param_126",
1457
+ "shape": [
1458
+ 11264,
1459
+ 512
1460
+ ],
1461
+ "dtype": "uint32",
1462
+ "format": "raw",
1463
+ "nbytes": 23068672,
1464
+ "byteOffset": 0
1465
+ }
1466
+ ]
1467
+ },
1468
+ {
1469
+ "dataPath": "params_shard_25.bin",
1470
+ "format": "raw-shard",
1471
+ "nbytes": 23732224,
1472
+ "records": [
1473
+ {
1474
+ "name": "param_118",
1475
+ "shape": [
1476
+ 2048,
1477
+ 1408
1478
+ ],
1479
+ "dtype": "uint32",
1480
+ "format": "raw",
1481
+ "nbytes": 11534336,
1482
+ "byteOffset": 0
1483
+ },
1484
+ {
1485
+ "name": "param_119",
1486
+ "shape": [
1487
+ 2048,
1488
+ 176
1489
+ ],
1490
+ "dtype": "float16",
1491
+ "format": "raw",
1492
+ "nbytes": 720896,
1493
+ "byteOffset": 11534336
1494
+ },
1495
+ {
1496
+ "name": "param_120",
1497
+ "shape": [
1498
+ 2048
1499
+ ],
1500
+ "dtype": "float16",
1501
+ "format": "raw",
1502
+ "nbytes": 4096,
1503
+ "byteOffset": 12255232
1504
+ },
1505
+ {
1506
+ "name": "param_121",
1507
+ "shape": [
1508
+ 2048
1509
+ ],
1510
+ "dtype": "float16",
1511
+ "format": "raw",
1512
+ "nbytes": 4096,
1513
+ "byteOffset": 12259328
1514
+ },
1515
+ {
1516
+ "name": "param_122",
1517
+ "shape": [
1518
+ 2560,
1519
+ 512
1520
+ ],
1521
+ "dtype": "uint32",
1522
+ "format": "raw",
1523
+ "nbytes": 5242880,
1524
+ "byteOffset": 12263424
1525
+ },
1526
+ {
1527
+ "name": "param_123",
1528
+ "shape": [
1529
+ 2560,
1530
+ 64
1531
+ ],
1532
+ "dtype": "float16",
1533
+ "format": "raw",
1534
+ "nbytes": 327680,
1535
+ "byteOffset": 17506304
1536
+ },
1537
+ {
1538
+ "name": "param_124",
1539
+ "shape": [
1540
+ 2048,
1541
+ 512
1542
+ ],
1543
+ "dtype": "uint32",
1544
+ "format": "raw",
1545
+ "nbytes": 4194304,
1546
+ "byteOffset": 17833984
1547
+ },
1548
+ {
1549
+ "name": "param_125",
1550
+ "shape": [
1551
+ 2048,
1552
+ 64
1553
+ ],
1554
+ "dtype": "float16",
1555
+ "format": "raw",
1556
+ "nbytes": 262144,
1557
+ "byteOffset": 22028288
1558
+ },
1559
+ {
1560
+ "name": "param_127",
1561
+ "shape": [
1562
+ 11264,
1563
+ 64
1564
+ ],
1565
+ "dtype": "float16",
1566
+ "format": "raw",
1567
+ "nbytes": 1441792,
1568
+ "byteOffset": 22290432
1569
+ }
1570
+ ]
1571
+ },
1572
+ {
1573
+ "dataPath": "params_shard_26.bin",
1574
+ "format": "raw-shard",
1575
+ "nbytes": 23068672,
1576
+ "records": [
1577
+ {
1578
+ "name": "param_136",
1579
+ "shape": [
1580
+ 11264,
1581
+ 512
1582
+ ],
1583
+ "dtype": "uint32",
1584
+ "format": "raw",
1585
+ "nbytes": 23068672,
1586
+ "byteOffset": 0
1587
+ }
1588
+ ]
1589
+ },
1590
+ {
1591
+ "dataPath": "params_shard_27.bin",
1592
+ "format": "raw-shard",
1593
+ "nbytes": 23732224,
1594
+ "records": [
1595
+ {
1596
+ "name": "param_128",
1597
+ "shape": [
1598
+ 2048,
1599
+ 1408
1600
+ ],
1601
+ "dtype": "uint32",
1602
+ "format": "raw",
1603
+ "nbytes": 11534336,
1604
+ "byteOffset": 0
1605
+ },
1606
+ {
1607
+ "name": "param_129",
1608
+ "shape": [
1609
+ 2048,
1610
+ 176
1611
+ ],
1612
+ "dtype": "float16",
1613
+ "format": "raw",
1614
+ "nbytes": 720896,
1615
+ "byteOffset": 11534336
1616
+ },
1617
+ {
1618
+ "name": "param_130",
1619
+ "shape": [
1620
+ 2048
1621
+ ],
1622
+ "dtype": "float16",
1623
+ "format": "raw",
1624
+ "nbytes": 4096,
1625
+ "byteOffset": 12255232
1626
+ },
1627
+ {
1628
+ "name": "param_131",
1629
+ "shape": [
1630
+ 2048
1631
+ ],
1632
+ "dtype": "float16",
1633
+ "format": "raw",
1634
+ "nbytes": 4096,
1635
+ "byteOffset": 12259328
1636
+ },
1637
+ {
1638
+ "name": "param_132",
1639
+ "shape": [
1640
+ 2560,
1641
+ 512
1642
+ ],
1643
+ "dtype": "uint32",
1644
+ "format": "raw",
1645
+ "nbytes": 5242880,
1646
+ "byteOffset": 12263424
1647
+ },
1648
+ {
1649
+ "name": "param_133",
1650
+ "shape": [
1651
+ 2560,
1652
+ 64
1653
+ ],
1654
+ "dtype": "float16",
1655
+ "format": "raw",
1656
+ "nbytes": 327680,
1657
+ "byteOffset": 17506304
1658
+ },
1659
+ {
1660
+ "name": "param_134",
1661
+ "shape": [
1662
+ 2048,
1663
+ 512
1664
+ ],
1665
+ "dtype": "uint32",
1666
+ "format": "raw",
1667
+ "nbytes": 4194304,
1668
+ "byteOffset": 17833984
1669
+ },
1670
+ {
1671
+ "name": "param_135",
1672
+ "shape": [
1673
+ 2048,
1674
+ 64
1675
+ ],
1676
+ "dtype": "float16",
1677
+ "format": "raw",
1678
+ "nbytes": 262144,
1679
+ "byteOffset": 22028288
1680
+ },
1681
+ {
1682
+ "name": "param_137",
1683
+ "shape": [
1684
+ 11264,
1685
+ 64
1686
+ ],
1687
+ "dtype": "float16",
1688
+ "format": "raw",
1689
+ "nbytes": 1441792,
1690
+ "byteOffset": 22290432
1691
+ }
1692
+ ]
1693
+ },
1694
+ {
1695
+ "dataPath": "params_shard_28.bin",
1696
+ "format": "raw-shard",
1697
+ "nbytes": 23068672,
1698
+ "records": [
1699
+ {
1700
+ "name": "param_146",
1701
+ "shape": [
1702
+ 11264,
1703
+ 512
1704
+ ],
1705
+ "dtype": "uint32",
1706
+ "format": "raw",
1707
+ "nbytes": 23068672,
1708
+ "byteOffset": 0
1709
+ }
1710
+ ]
1711
+ },
1712
+ {
1713
+ "dataPath": "params_shard_29.bin",
1714
+ "format": "raw-shard",
1715
+ "nbytes": 23732224,
1716
+ "records": [
1717
+ {
1718
+ "name": "param_138",
1719
+ "shape": [
1720
+ 2048,
1721
+ 1408
1722
+ ],
1723
+ "dtype": "uint32",
1724
+ "format": "raw",
1725
+ "nbytes": 11534336,
1726
+ "byteOffset": 0
1727
+ },
1728
+ {
1729
+ "name": "param_139",
1730
+ "shape": [
1731
+ 2048,
1732
+ 176
1733
+ ],
1734
+ "dtype": "float16",
1735
+ "format": "raw",
1736
+ "nbytes": 720896,
1737
+ "byteOffset": 11534336
1738
+ },
1739
+ {
1740
+ "name": "param_140",
1741
+ "shape": [
1742
+ 2048
1743
+ ],
1744
+ "dtype": "float16",
1745
+ "format": "raw",
1746
+ "nbytes": 4096,
1747
+ "byteOffset": 12255232
1748
+ },
1749
+ {
1750
+ "name": "param_141",
1751
+ "shape": [
1752
+ 2048
1753
+ ],
1754
+ "dtype": "float16",
1755
+ "format": "raw",
1756
+ "nbytes": 4096,
1757
+ "byteOffset": 12259328
1758
+ },
1759
+ {
1760
+ "name": "param_142",
1761
+ "shape": [
1762
+ 2560,
1763
+ 512
1764
+ ],
1765
+ "dtype": "uint32",
1766
+ "format": "raw",
1767
+ "nbytes": 5242880,
1768
+ "byteOffset": 12263424
1769
+ },
1770
+ {
1771
+ "name": "param_143",
1772
+ "shape": [
1773
+ 2560,
1774
+ 64
1775
+ ],
1776
+ "dtype": "float16",
1777
+ "format": "raw",
1778
+ "nbytes": 327680,
1779
+ "byteOffset": 17506304
1780
+ },
1781
+ {
1782
+ "name": "param_144",
1783
+ "shape": [
1784
+ 2048,
1785
+ 512
1786
+ ],
1787
+ "dtype": "uint32",
1788
+ "format": "raw",
1789
+ "nbytes": 4194304,
1790
+ "byteOffset": 17833984
1791
+ },
1792
+ {
1793
+ "name": "param_145",
1794
+ "shape": [
1795
+ 2048,
1796
+ 64
1797
+ ],
1798
+ "dtype": "float16",
1799
+ "format": "raw",
1800
+ "nbytes": 262144,
1801
+ "byteOffset": 22028288
1802
+ },
1803
+ {
1804
+ "name": "param_147",
1805
+ "shape": [
1806
+ 11264,
1807
+ 64
1808
+ ],
1809
+ "dtype": "float16",
1810
+ "format": "raw",
1811
+ "nbytes": 1441792,
1812
+ "byteOffset": 22290432
1813
+ }
1814
+ ]
1815
+ },
1816
+ {
1817
+ "dataPath": "params_shard_30.bin",
1818
+ "format": "raw-shard",
1819
+ "nbytes": 23068672,
1820
+ "records": [
1821
+ {
1822
+ "name": "param_156",
1823
+ "shape": [
1824
+ 11264,
1825
+ 512
1826
+ ],
1827
+ "dtype": "uint32",
1828
+ "format": "raw",
1829
+ "nbytes": 23068672,
1830
+ "byteOffset": 0
1831
+ }
1832
+ ]
1833
+ },
1834
+ {
1835
+ "dataPath": "params_shard_31.bin",
1836
+ "format": "raw-shard",
1837
+ "nbytes": 23732224,
1838
+ "records": [
1839
+ {
1840
+ "name": "param_148",
1841
+ "shape": [
1842
+ 2048,
1843
+ 1408
1844
+ ],
1845
+ "dtype": "uint32",
1846
+ "format": "raw",
1847
+ "nbytes": 11534336,
1848
+ "byteOffset": 0
1849
+ },
1850
+ {
1851
+ "name": "param_149",
1852
+ "shape": [
1853
+ 2048,
1854
+ 176
1855
+ ],
1856
+ "dtype": "float16",
1857
+ "format": "raw",
1858
+ "nbytes": 720896,
1859
+ "byteOffset": 11534336
1860
+ },
1861
+ {
1862
+ "name": "param_150",
1863
+ "shape": [
1864
+ 2048
1865
+ ],
1866
+ "dtype": "float16",
1867
+ "format": "raw",
1868
+ "nbytes": 4096,
1869
+ "byteOffset": 12255232
1870
+ },
1871
+ {
1872
+ "name": "param_151",
1873
+ "shape": [
1874
+ 2048
1875
+ ],
1876
+ "dtype": "float16",
1877
+ "format": "raw",
1878
+ "nbytes": 4096,
1879
+ "byteOffset": 12259328
1880
+ },
1881
+ {
1882
+ "name": "param_152",
1883
+ "shape": [
1884
+ 2560,
1885
+ 512
1886
+ ],
1887
+ "dtype": "uint32",
1888
+ "format": "raw",
1889
+ "nbytes": 5242880,
1890
+ "byteOffset": 12263424
1891
+ },
1892
+ {
1893
+ "name": "param_153",
1894
+ "shape": [
1895
+ 2560,
1896
+ 64
1897
+ ],
1898
+ "dtype": "float16",
1899
+ "format": "raw",
1900
+ "nbytes": 327680,
1901
+ "byteOffset": 17506304
1902
+ },
1903
+ {
1904
+ "name": "param_154",
1905
+ "shape": [
1906
+ 2048,
1907
+ 512
1908
+ ],
1909
+ "dtype": "uint32",
1910
+ "format": "raw",
1911
+ "nbytes": 4194304,
1912
+ "byteOffset": 17833984
1913
+ },
1914
+ {
1915
+ "name": "param_155",
1916
+ "shape": [
1917
+ 2048,
1918
+ 64
1919
+ ],
1920
+ "dtype": "float16",
1921
+ "format": "raw",
1922
+ "nbytes": 262144,
1923
+ "byteOffset": 22028288
1924
+ },
1925
+ {
1926
+ "name": "param_157",
1927
+ "shape": [
1928
+ 11264,
1929
+ 64
1930
+ ],
1931
+ "dtype": "float16",
1932
+ "format": "raw",
1933
+ "nbytes": 1441792,
1934
+ "byteOffset": 22290432
1935
+ }
1936
+ ]
1937
+ },
1938
+ {
1939
+ "dataPath": "params_shard_32.bin",
1940
+ "format": "raw-shard",
1941
+ "nbytes": 23068672,
1942
+ "records": [
1943
+ {
1944
+ "name": "param_166",
1945
+ "shape": [
1946
+ 11264,
1947
+ 512
1948
+ ],
1949
+ "dtype": "uint32",
1950
+ "format": "raw",
1951
+ "nbytes": 23068672,
1952
+ "byteOffset": 0
1953
+ }
1954
+ ]
1955
+ },
1956
+ {
1957
+ "dataPath": "params_shard_33.bin",
1958
+ "format": "raw-shard",
1959
+ "nbytes": 23732224,
1960
+ "records": [
1961
+ {
1962
+ "name": "param_158",
1963
+ "shape": [
1964
+ 2048,
1965
+ 1408
1966
+ ],
1967
+ "dtype": "uint32",
1968
+ "format": "raw",
1969
+ "nbytes": 11534336,
1970
+ "byteOffset": 0
1971
+ },
1972
+ {
1973
+ "name": "param_159",
1974
+ "shape": [
1975
+ 2048,
1976
+ 176
1977
+ ],
1978
+ "dtype": "float16",
1979
+ "format": "raw",
1980
+ "nbytes": 720896,
1981
+ "byteOffset": 11534336
1982
+ },
1983
+ {
1984
+ "name": "param_160",
1985
+ "shape": [
1986
+ 2048
1987
+ ],
1988
+ "dtype": "float16",
1989
+ "format": "raw",
1990
+ "nbytes": 4096,
1991
+ "byteOffset": 12255232
1992
+ },
1993
+ {
1994
+ "name": "param_161",
1995
+ "shape": [
1996
+ 2048
1997
+ ],
1998
+ "dtype": "float16",
1999
+ "format": "raw",
2000
+ "nbytes": 4096,
2001
+ "byteOffset": 12259328
2002
+ },
2003
+ {
2004
+ "name": "param_162",
2005
+ "shape": [
2006
+ 2560,
2007
+ 512
2008
+ ],
2009
+ "dtype": "uint32",
2010
+ "format": "raw",
2011
+ "nbytes": 5242880,
2012
+ "byteOffset": 12263424
2013
+ },
2014
+ {
2015
+ "name": "param_163",
2016
+ "shape": [
2017
+ 2560,
2018
+ 64
2019
+ ],
2020
+ "dtype": "float16",
2021
+ "format": "raw",
2022
+ "nbytes": 327680,
2023
+ "byteOffset": 17506304
2024
+ },
2025
+ {
2026
+ "name": "param_164",
2027
+ "shape": [
2028
+ 2048,
2029
+ 512
2030
+ ],
2031
+ "dtype": "uint32",
2032
+ "format": "raw",
2033
+ "nbytes": 4194304,
2034
+ "byteOffset": 17833984
2035
+ },
2036
+ {
2037
+ "name": "param_165",
2038
+ "shape": [
2039
+ 2048,
2040
+ 64
2041
+ ],
2042
+ "dtype": "float16",
2043
+ "format": "raw",
2044
+ "nbytes": 262144,
2045
+ "byteOffset": 22028288
2046
+ },
2047
+ {
2048
+ "name": "param_167",
2049
+ "shape": [
2050
+ 11264,
2051
+ 64
2052
+ ],
2053
+ "dtype": "float16",
2054
+ "format": "raw",
2055
+ "nbytes": 1441792,
2056
+ "byteOffset": 22290432
2057
+ }
2058
+ ]
2059
+ },
2060
+ {
2061
+ "dataPath": "params_shard_34.bin",
2062
+ "format": "raw-shard",
2063
+ "nbytes": 23068672,
2064
+ "records": [
2065
+ {
2066
+ "name": "param_176",
2067
+ "shape": [
2068
+ 11264,
2069
+ 512
2070
+ ],
2071
+ "dtype": "uint32",
2072
+ "format": "raw",
2073
+ "nbytes": 23068672,
2074
+ "byteOffset": 0
2075
+ }
2076
+ ]
2077
+ },
2078
+ {
2079
+ "dataPath": "params_shard_35.bin",
2080
+ "format": "raw-shard",
2081
+ "nbytes": 23732224,
2082
+ "records": [
2083
+ {
2084
+ "name": "param_168",
2085
+ "shape": [
2086
+ 2048,
2087
+ 1408
2088
+ ],
2089
+ "dtype": "uint32",
2090
+ "format": "raw",
2091
+ "nbytes": 11534336,
2092
+ "byteOffset": 0
2093
+ },
2094
+ {
2095
+ "name": "param_169",
2096
+ "shape": [
2097
+ 2048,
2098
+ 176
2099
+ ],
2100
+ "dtype": "float16",
2101
+ "format": "raw",
2102
+ "nbytes": 720896,
2103
+ "byteOffset": 11534336
2104
+ },
2105
+ {
2106
+ "name": "param_170",
2107
+ "shape": [
2108
+ 2048
2109
+ ],
2110
+ "dtype": "float16",
2111
+ "format": "raw",
2112
+ "nbytes": 4096,
2113
+ "byteOffset": 12255232
2114
+ },
2115
+ {
2116
+ "name": "param_171",
2117
+ "shape": [
2118
+ 2048
2119
+ ],
2120
+ "dtype": "float16",
2121
+ "format": "raw",
2122
+ "nbytes": 4096,
2123
+ "byteOffset": 12259328
2124
+ },
2125
+ {
2126
+ "name": "param_172",
2127
+ "shape": [
2128
+ 2560,
2129
+ 512
2130
+ ],
2131
+ "dtype": "uint32",
2132
+ "format": "raw",
2133
+ "nbytes": 5242880,
2134
+ "byteOffset": 12263424
2135
+ },
2136
+ {
2137
+ "name": "param_173",
2138
+ "shape": [
2139
+ 2560,
2140
+ 64
2141
+ ],
2142
+ "dtype": "float16",
2143
+ "format": "raw",
2144
+ "nbytes": 327680,
2145
+ "byteOffset": 17506304
2146
+ },
2147
+ {
2148
+ "name": "param_174",
2149
+ "shape": [
2150
+ 2048,
2151
+ 512
2152
+ ],
2153
+ "dtype": "uint32",
2154
+ "format": "raw",
2155
+ "nbytes": 4194304,
2156
+ "byteOffset": 17833984
2157
+ },
2158
+ {
2159
+ "name": "param_175",
2160
+ "shape": [
2161
+ 2048,
2162
+ 64
2163
+ ],
2164
+ "dtype": "float16",
2165
+ "format": "raw",
2166
+ "nbytes": 262144,
2167
+ "byteOffset": 22028288
2168
+ },
2169
+ {
2170
+ "name": "param_177",
2171
+ "shape": [
2172
+ 11264,
2173
+ 64
2174
+ ],
2175
+ "dtype": "float16",
2176
+ "format": "raw",
2177
+ "nbytes": 1441792,
2178
+ "byteOffset": 22290432
2179
+ }
2180
+ ]
2181
+ },
2182
+ {
2183
+ "dataPath": "params_shard_36.bin",
2184
+ "format": "raw-shard",
2185
+ "nbytes": 23068672,
2186
+ "records": [
2187
+ {
2188
+ "name": "param_186",
2189
+ "shape": [
2190
+ 11264,
2191
+ 512
2192
+ ],
2193
+ "dtype": "uint32",
2194
+ "format": "raw",
2195
+ "nbytes": 23068672,
2196
+ "byteOffset": 0
2197
+ }
2198
+ ]
2199
+ },
2200
+ {
2201
+ "dataPath": "params_shard_37.bin",
2202
+ "format": "raw-shard",
2203
+ "nbytes": 23732224,
2204
+ "records": [
2205
+ {
2206
+ "name": "param_178",
2207
+ "shape": [
2208
+ 2048,
2209
+ 1408
2210
+ ],
2211
+ "dtype": "uint32",
2212
+ "format": "raw",
2213
+ "nbytes": 11534336,
2214
+ "byteOffset": 0
2215
+ },
2216
+ {
2217
+ "name": "param_179",
2218
+ "shape": [
2219
+ 2048,
2220
+ 176
2221
+ ],
2222
+ "dtype": "float16",
2223
+ "format": "raw",
2224
+ "nbytes": 720896,
2225
+ "byteOffset": 11534336
2226
+ },
2227
+ {
2228
+ "name": "param_180",
2229
+ "shape": [
2230
+ 2048
2231
+ ],
2232
+ "dtype": "float16",
2233
+ "format": "raw",
2234
+ "nbytes": 4096,
2235
+ "byteOffset": 12255232
2236
+ },
2237
+ {
2238
+ "name": "param_181",
2239
+ "shape": [
2240
+ 2048
2241
+ ],
2242
+ "dtype": "float16",
2243
+ "format": "raw",
2244
+ "nbytes": 4096,
2245
+ "byteOffset": 12259328
2246
+ },
2247
+ {
2248
+ "name": "param_182",
2249
+ "shape": [
2250
+ 2560,
2251
+ 512
2252
+ ],
2253
+ "dtype": "uint32",
2254
+ "format": "raw",
2255
+ "nbytes": 5242880,
2256
+ "byteOffset": 12263424
2257
+ },
2258
+ {
2259
+ "name": "param_183",
2260
+ "shape": [
2261
+ 2560,
2262
+ 64
2263
+ ],
2264
+ "dtype": "float16",
2265
+ "format": "raw",
2266
+ "nbytes": 327680,
2267
+ "byteOffset": 17506304
2268
+ },
2269
+ {
2270
+ "name": "param_184",
2271
+ "shape": [
2272
+ 2048,
2273
+ 512
2274
+ ],
2275
+ "dtype": "uint32",
2276
+ "format": "raw",
2277
+ "nbytes": 4194304,
2278
+ "byteOffset": 17833984
2279
+ },
2280
+ {
2281
+ "name": "param_185",
2282
+ "shape": [
2283
+ 2048,
2284
+ 64
2285
+ ],
2286
+ "dtype": "float16",
2287
+ "format": "raw",
2288
+ "nbytes": 262144,
2289
+ "byteOffset": 22028288
2290
+ },
2291
+ {
2292
+ "name": "param_187",
2293
+ "shape": [
2294
+ 11264,
2295
+ 64
2296
+ ],
2297
+ "dtype": "float16",
2298
+ "format": "raw",
2299
+ "nbytes": 1441792,
2300
+ "byteOffset": 22290432
2301
+ }
2302
+ ]
2303
+ },
2304
+ {
2305
+ "dataPath": "params_shard_38.bin",
2306
+ "format": "raw-shard",
2307
+ "nbytes": 23068672,
2308
+ "records": [
2309
+ {
2310
+ "name": "param_196",
2311
+ "shape": [
2312
+ 11264,
2313
+ 512
2314
+ ],
2315
+ "dtype": "uint32",
2316
+ "format": "raw",
2317
+ "nbytes": 23068672,
2318
+ "byteOffset": 0
2319
+ }
2320
+ ]
2321
+ },
2322
+ {
2323
+ "dataPath": "params_shard_39.bin",
2324
+ "format": "raw-shard",
2325
+ "nbytes": 23732224,
2326
+ "records": [
2327
+ {
2328
+ "name": "param_188",
2329
+ "shape": [
2330
+ 2048,
2331
+ 1408
2332
+ ],
2333
+ "dtype": "uint32",
2334
+ "format": "raw",
2335
+ "nbytes": 11534336,
2336
+ "byteOffset": 0
2337
+ },
2338
+ {
2339
+ "name": "param_189",
2340
+ "shape": [
2341
+ 2048,
2342
+ 176
2343
+ ],
2344
+ "dtype": "float16",
2345
+ "format": "raw",
2346
+ "nbytes": 720896,
2347
+ "byteOffset": 11534336
2348
+ },
2349
+ {
2350
+ "name": "param_190",
2351
+ "shape": [
2352
+ 2048
2353
+ ],
2354
+ "dtype": "float16",
2355
+ "format": "raw",
2356
+ "nbytes": 4096,
2357
+ "byteOffset": 12255232
2358
+ },
2359
+ {
2360
+ "name": "param_191",
2361
+ "shape": [
2362
+ 2048
2363
+ ],
2364
+ "dtype": "float16",
2365
+ "format": "raw",
2366
+ "nbytes": 4096,
2367
+ "byteOffset": 12259328
2368
+ },
2369
+ {
2370
+ "name": "param_192",
2371
+ "shape": [
2372
+ 2560,
2373
+ 512
2374
+ ],
2375
+ "dtype": "uint32",
2376
+ "format": "raw",
2377
+ "nbytes": 5242880,
2378
+ "byteOffset": 12263424
2379
+ },
2380
+ {
2381
+ "name": "param_193",
2382
+ "shape": [
2383
+ 2560,
2384
+ 64
2385
+ ],
2386
+ "dtype": "float16",
2387
+ "format": "raw",
2388
+ "nbytes": 327680,
2389
+ "byteOffset": 17506304
2390
+ },
2391
+ {
2392
+ "name": "param_194",
2393
+ "shape": [
2394
+ 2048,
2395
+ 512
2396
+ ],
2397
+ "dtype": "uint32",
2398
+ "format": "raw",
2399
+ "nbytes": 4194304,
2400
+ "byteOffset": 17833984
2401
+ },
2402
+ {
2403
+ "name": "param_195",
2404
+ "shape": [
2405
+ 2048,
2406
+ 64
2407
+ ],
2408
+ "dtype": "float16",
2409
+ "format": "raw",
2410
+ "nbytes": 262144,
2411
+ "byteOffset": 22028288
2412
+ },
2413
+ {
2414
+ "name": "param_197",
2415
+ "shape": [
2416
+ 11264,
2417
+ 64
2418
+ ],
2419
+ "dtype": "float16",
2420
+ "format": "raw",
2421
+ "nbytes": 1441792,
2422
+ "byteOffset": 22290432
2423
+ }
2424
+ ]
2425
+ },
2426
+ {
2427
+ "dataPath": "params_shard_40.bin",
2428
+ "format": "raw-shard",
2429
+ "nbytes": 23068672,
2430
+ "records": [
2431
+ {
2432
+ "name": "param_206",
2433
+ "shape": [
2434
+ 11264,
2435
+ 512
2436
+ ],
2437
+ "dtype": "uint32",
2438
+ "format": "raw",
2439
+ "nbytes": 23068672,
2440
+ "byteOffset": 0
2441
+ }
2442
+ ]
2443
+ },
2444
+ {
2445
+ "dataPath": "params_shard_41.bin",
2446
+ "format": "raw-shard",
2447
+ "nbytes": 23732224,
2448
+ "records": [
2449
+ {
2450
+ "name": "param_198",
2451
+ "shape": [
2452
+ 2048,
2453
+ 1408
2454
+ ],
2455
+ "dtype": "uint32",
2456
+ "format": "raw",
2457
+ "nbytes": 11534336,
2458
+ "byteOffset": 0
2459
+ },
2460
+ {
2461
+ "name": "param_199",
2462
+ "shape": [
2463
+ 2048,
2464
+ 176
2465
+ ],
2466
+ "dtype": "float16",
2467
+ "format": "raw",
2468
+ "nbytes": 720896,
2469
+ "byteOffset": 11534336
2470
+ },
2471
+ {
2472
+ "name": "param_200",
2473
+ "shape": [
2474
+ 2048
2475
+ ],
2476
+ "dtype": "float16",
2477
+ "format": "raw",
2478
+ "nbytes": 4096,
2479
+ "byteOffset": 12255232
2480
+ },
2481
+ {
2482
+ "name": "param_201",
2483
+ "shape": [
2484
+ 2048
2485
+ ],
2486
+ "dtype": "float16",
2487
+ "format": "raw",
2488
+ "nbytes": 4096,
2489
+ "byteOffset": 12259328
2490
+ },
2491
+ {
2492
+ "name": "param_202",
2493
+ "shape": [
2494
+ 2560,
2495
+ 512
2496
+ ],
2497
+ "dtype": "uint32",
2498
+ "format": "raw",
2499
+ "nbytes": 5242880,
2500
+ "byteOffset": 12263424
2501
+ },
2502
+ {
2503
+ "name": "param_203",
2504
+ "shape": [
2505
+ 2560,
2506
+ 64
2507
+ ],
2508
+ "dtype": "float16",
2509
+ "format": "raw",
2510
+ "nbytes": 327680,
2511
+ "byteOffset": 17506304
2512
+ },
2513
+ {
2514
+ "name": "param_204",
2515
+ "shape": [
2516
+ 2048,
2517
+ 512
2518
+ ],
2519
+ "dtype": "uint32",
2520
+ "format": "raw",
2521
+ "nbytes": 4194304,
2522
+ "byteOffset": 17833984
2523
+ },
2524
+ {
2525
+ "name": "param_205",
2526
+ "shape": [
2527
+ 2048,
2528
+ 64
2529
+ ],
2530
+ "dtype": "float16",
2531
+ "format": "raw",
2532
+ "nbytes": 262144,
2533
+ "byteOffset": 22028288
2534
+ },
2535
+ {
2536
+ "name": "param_207",
2537
+ "shape": [
2538
+ 11264,
2539
+ 64
2540
+ ],
2541
+ "dtype": "float16",
2542
+ "format": "raw",
2543
+ "nbytes": 1441792,
2544
+ "byteOffset": 22290432
2545
+ }
2546
+ ]
2547
+ },
2548
+ {
2549
+ "dataPath": "params_shard_42.bin",
2550
+ "format": "raw-shard",
2551
+ "nbytes": 23068672,
2552
+ "records": [
2553
+ {
2554
+ "name": "param_216",
2555
+ "shape": [
2556
+ 11264,
2557
+ 512
2558
+ ],
2559
+ "dtype": "uint32",
2560
+ "format": "raw",
2561
+ "nbytes": 23068672,
2562
+ "byteOffset": 0
2563
+ }
2564
+ ]
2565
+ },
2566
+ {
2567
+ "dataPath": "params_shard_43.bin",
2568
+ "format": "raw-shard",
2569
+ "nbytes": 23732224,
2570
+ "records": [
2571
+ {
2572
+ "name": "param_208",
2573
+ "shape": [
2574
+ 2048,
2575
+ 1408
2576
+ ],
2577
+ "dtype": "uint32",
2578
+ "format": "raw",
2579
+ "nbytes": 11534336,
2580
+ "byteOffset": 0
2581
+ },
2582
+ {
2583
+ "name": "param_209",
2584
+ "shape": [
2585
+ 2048,
2586
+ 176
2587
+ ],
2588
+ "dtype": "float16",
2589
+ "format": "raw",
2590
+ "nbytes": 720896,
2591
+ "byteOffset": 11534336
2592
+ },
2593
+ {
2594
+ "name": "param_210",
2595
+ "shape": [
2596
+ 2048
2597
+ ],
2598
+ "dtype": "float16",
2599
+ "format": "raw",
2600
+ "nbytes": 4096,
2601
+ "byteOffset": 12255232
2602
+ },
2603
+ {
2604
+ "name": "param_211",
2605
+ "shape": [
2606
+ 2048
2607
+ ],
2608
+ "dtype": "float16",
2609
+ "format": "raw",
2610
+ "nbytes": 4096,
2611
+ "byteOffset": 12259328
2612
+ },
2613
+ {
2614
+ "name": "param_212",
2615
+ "shape": [
2616
+ 2560,
2617
+ 512
2618
+ ],
2619
+ "dtype": "uint32",
2620
+ "format": "raw",
2621
+ "nbytes": 5242880,
2622
+ "byteOffset": 12263424
2623
+ },
2624
+ {
2625
+ "name": "param_213",
2626
+ "shape": [
2627
+ 2560,
2628
+ 64
2629
+ ],
2630
+ "dtype": "float16",
2631
+ "format": "raw",
2632
+ "nbytes": 327680,
2633
+ "byteOffset": 17506304
2634
+ },
2635
+ {
2636
+ "name": "param_214",
2637
+ "shape": [
2638
+ 2048,
2639
+ 512
2640
+ ],
2641
+ "dtype": "uint32",
2642
+ "format": "raw",
2643
+ "nbytes": 4194304,
2644
+ "byteOffset": 17833984
2645
+ },
2646
+ {
2647
+ "name": "param_215",
2648
+ "shape": [
2649
+ 2048,
2650
+ 64
2651
+ ],
2652
+ "dtype": "float16",
2653
+ "format": "raw",
2654
+ "nbytes": 262144,
2655
+ "byteOffset": 22028288
2656
+ },
2657
+ {
2658
+ "name": "param_217",
2659
+ "shape": [
2660
+ 11264,
2661
+ 64
2662
+ ],
2663
+ "dtype": "float16",
2664
+ "format": "raw",
2665
+ "nbytes": 1441792,
2666
+ "byteOffset": 22290432
2667
+ }
2668
+ ]
2669
+ },
2670
+ {
2671
+ "dataPath": "params_shard_44.bin",
2672
+ "format": "raw-shard",
2673
+ "nbytes": 65542144,
2674
+ "records": [
2675
+ {
2676
+ "name": "param_223",
2677
+ "shape": [
2678
+ 32003,
2679
+ 512
2680
+ ],
2681
+ "dtype": "uint32",
2682
+ "format": "raw",
2683
+ "nbytes": 65542144,
2684
+ "byteOffset": 0
2685
+ }
2686
+ ]
2687
+ },
2688
+ {
2689
+ "dataPath": "params_shard_45.bin",
2690
+ "format": "raw-shard",
2691
+ "nbytes": 16888192,
2692
+ "records": [
2693
+ {
2694
+ "name": "param_218",
2695
+ "shape": [
2696
+ 2048,
2697
+ 1408
2698
+ ],
2699
+ "dtype": "uint32",
2700
+ "format": "raw",
2701
+ "nbytes": 11534336,
2702
+ "byteOffset": 0
2703
+ },
2704
+ {
2705
+ "name": "param_219",
2706
+ "shape": [
2707
+ 2048,
2708
+ 176
2709
+ ],
2710
+ "dtype": "float16",
2711
+ "format": "raw",
2712
+ "nbytes": 720896,
2713
+ "byteOffset": 11534336
2714
+ },
2715
+ {
2716
+ "name": "param_220",
2717
+ "shape": [
2718
+ 2048
2719
+ ],
2720
+ "dtype": "float16",
2721
+ "format": "raw",
2722
+ "nbytes": 4096,
2723
+ "byteOffset": 12255232
2724
+ },
2725
+ {
2726
+ "name": "param_221",
2727
+ "shape": [
2728
+ 2048
2729
+ ],
2730
+ "dtype": "float16",
2731
+ "format": "raw",
2732
+ "nbytes": 4096,
2733
+ "byteOffset": 12259328
2734
+ },
2735
+ {
2736
+ "name": "param_222",
2737
+ "shape": [
2738
+ 2048
2739
+ ],
2740
+ "dtype": "float16",
2741
+ "format": "raw",
2742
+ "nbytes": 4096,
2743
+ "byteOffset": 12263424
2744
+ },
2745
+ {
2746
+ "name": "param_224",
2747
+ "shape": [
2748
+ 32003,
2749
+ 64
2750
+ ],
2751
+ "dtype": "float16",
2752
+ "format": "raw",
2753
+ "nbytes": 4096384,
2754
+ "byteOffset": 12267520
2755
+ },
2756
+ {
2757
+ "name": "param_225",
2758
+ "shape": [
2759
+ 2048,
2760
+ 64
2761
+ ],
2762
+ "dtype": "float16",
2763
+ "format": "raw",
2764
+ "nbytes": 262144,
2765
+ "byteOffset": 16363904
2766
+ },
2767
+ {
2768
+ "name": "param_226",
2769
+ "shape": [
2770
+ 2048,
2771
+ 64
2772
+ ],
2773
+ "dtype": "float16",
2774
+ "format": "raw",
2775
+ "nbytes": 262144,
2776
+ "byteOffset": 16626048
2777
+ }
2778
+ ]
2779
+ }
2780
+ ]
2781
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d4a21256a91110ddff364da90324e4c8d29b62ad487f98230339570a733ffa
3
+ size 65542144
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc521d1639fc243d52f34c9f96147f5217530a2464d0b0136e3a98ffdaec73d0
3
+ size 23068672
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49cfa9db5f28f2f3632a5b8ae81c44af56e4e020ca50070c0452c38dc01b4fc5
3
+ size 23068672
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e86c1879cfa4b3c229a5035226811426dde945dbf0fd1ff998a388d0c4516e
3
+ size 23732224
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee469a18d6ee82b11723b0c40dace4f29a95b954e88578cb4e3fb0940d609ab
3
+ size 23068672
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4621b95ac52179e92f562c4fa1e0b04ca1b178e17fd1a750b1014e5a5d593e26
3
+ size 23732224
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45380888bc9701a835389151a9d74b0ae29ec1fd2b333226ea6b5ec77d9b416
3
+ size 23068672
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0abbf89187d9afcbbddfe730e94552df194a768453ca31ca48093f6714e50f9
3
+ size 23732224
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c38af2eb82b8ccd3ac0ffbbd365bacc3d2dee434fcdabf0a57851bafa02389
3
+ size 23068672
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1aa18bf831f8588036901b7165bbcb9932592e423b52492338c4fefbc14a799
3
+ size 23732224
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b309b1f790163644426f2c94eaaa45a1b80914c8e2bffbf4a42c26fb88a427
3
+ size 23068672
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b99ad32b66ec6e8526c064a282db38fc453de03cb1a68230cf6417c993841d92
3
+ size 23732224
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04b40b924204703791a22a71b3fd134b8547951edaccc85fc6833cf3b35372a
3
+ size 33399168
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e688344ca78969d9d1604889feb3cd235461e743e0fd49a4371b7cbde1e1dcbe
3
+ size 23068672
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31bfe3a21e020614e862305ca110a201b2853e34d71b83ba5fcbc32f1cd90d7f
3
+ size 23732224
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99912de37d588f445ec6ec5d08812edb98516bc727a0f2a2c104c03bc99486b8
3
+ size 23068672
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aeef9a026352be5ff793ff0c04aa5807c8bbba87497418ec14303efb5fd0ed3
3
+ size 23732224
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31fb494ee0fde1208a1ecd9749b27f9b961d6327d63da485fa133b2758668c21
3
+ size 23068672
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d825e235fb92c74d462970cc05024cf95b88ae6c5baf8ec8854b6af15258d1
3
+ size 23732224
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74645ec8b9b21333e5805486e6e1ff9b1f3f53fdabce8b731d33f672a0626bdf
3
+ size 23068672
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15242e7bb8d70e1a3ee860e55cda366cff7f8376d955e1c46a0620f02d870451
3
+ size 23732224
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77858aab69c3c908cd460a9a430218c997ae834b86deec3a2c692b932a4baaa
3
+ size 23068672
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545e9da1054e63f4eedd70b4e5236a0f1a1e2a668040d6fb343d96ec6d3b2868
3
+ size 23732224
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a5dc9ca1e1375a620b55a6546698e12968860edca6d31719d3d12d511e4573
3
+ size 28966912
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e73cbd58a8d8e36095ff17dde70f7ab377e5af9f2ca849b56b28dadbd47d4d
3
+ size 23068672
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1339fbb1c45367caf95430718f1c622077114faaae26666e3c5f638fc89e24c1
3
+ size 23732224
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4166790ad8faf8974875e6c57cfc6ce14cd7b9f646221f1f8111e95d7166ec09
3
+ size 23068672
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6e1e47a95d80f22de40c94f94920a871d50069562bf6ccb8e1e1a6ba197e2f
3
+ size 23732224
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b114e80b459835ca3b31b27a0455926129b18cd7144e591502d566d225db63cc
3
+ size 23068672
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a69ca578c18dae184dcc88e1a4f401a382b9f616d6d9a9906b1e7531f44f121
3
+ size 23732224
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa46f4c338bafb179530c54121e0dc5872a3e4eedb3149872627190d62a221d
3
+ size 23068672
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4f291ae760e6c067a254d300dd760e74428947f100967142679d014c006702
3
+ size 23732224
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35395c1cdf61295a4f74fcd15b97d290ac4939d1674a3b51f8e852e81e55efef
3
+ size 23068672
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb01c33ef025edd593740a08a461f141e2506a027f3831495f8d5c001937445
3
+ size 23732224
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48544fa96ac1f9159a2792bf83cb7414f98729fec119bf2e2eecf4477e8e3567
3
+ size 23068672
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f3c86d347cdb0866033e56c81dca7dd7b7a7babfb3e9f9dc202b15314e7f9d
3
+ size 23068672
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd2829afc0f1ae59b6118ba64ee000e6a839c30bcdd21f65ab15a546596e0b57
3
+ size 23732224
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31280272289f6340d0db8e01b9fbc9a6a455a1ab7d053547ce46c62b1ee629db
3
+ size 23068672
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ebca53a0ad1b0b9f9ac6bde555a14e6b7100f4426e456a6b72bf32ae478fd1
3
+ size 23732224
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080ff03fee0d70fa6c77621881f97e48acb3468082b72ebd3b98686bb326b1b5
3
+ size 65542144
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d851e0e686a445438388c520b719c9f37344244c0bb74c499a419f78898c4e4
3
+ size 16888192
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c4e6eae66c83b2d55b6885699c96e3986df8dc6417aa288760522819fbc330
3
+ size 23732224
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d26149d6f33bc4f83bfb246932ef2629c203422f251c65f7fc712d0d771347d
3
+ size 23068672
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66da5f68c1919979060c7d7ecd8f1654157be60a8f0c5c639fd88a24d261897d
3
+ size 23732224
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17128dbb02429f9d23cb2531875b8c7ff37c437f61c7798aa016f22fd2f155b5
3
+ size 23068672