add config.json
Browse files- .gitattributes +365 -0
- config.json +38 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,368 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
pytorch_model-00299-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
pytorch_model-00335-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
pytorch_model-00339-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
pytorch_model-00003-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
pytorch_model-00067-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
pytorch_model-00084-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
pytorch_model-00163-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
pytorch_model-00230-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
pytorch_model-00293-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
pytorch_model-00006-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
pytorch_model-00033-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
pytorch_model-00120-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
pytorch_model-00173-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
pytorch_model-00122-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
pytorch_model-00223-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
pytorch_model-00323-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
pytorch_model-00331-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
pytorch_model-00321-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
pytorch_model-00329-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
pytorch_model-00070-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
pytorch_model-00156-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
pytorch_model-00257-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
pytorch_model-00305-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
pytorch_model-00081-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
pytorch_model-00222-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
pytorch_model-00359-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
pytorch_model-00057-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
pytorch_model-00105-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
pytorch_model-00113-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
pytorch_model-00151-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
pytorch_model-00008-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
pytorch_model-00011-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
pytorch_model-00051-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
pytorch_model-00056-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
pytorch_model-00158-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
pytorch_model-00185-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
pytorch_model-00315-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
pytorch_model-00336-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
pytorch_model-00183-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
pytorch_model-00244-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
pytorch_model-00255-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
pytorch_model-00260-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
pytorch_model-00270-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
pytorch_model-00313-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
pytorch_model-00010-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
pytorch_model-00017-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
pytorch_model-00128-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
pytorch_model-00133-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
pytorch_model-00210-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
pytorch_model-00247-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
pytorch_model-00324-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
pytorch_model-00037-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
pytorch_model-00058-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
pytorch_model-00125-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
pytorch_model-00203-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
pytorch_model-00019-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
pytorch_model-00199-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
pytorch_model-00224-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
pytorch_model-00283-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
pytorch_model-00317-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
pytorch_model-00358-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
pytorch_model-00080-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
pytorch_model-00136-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
pytorch_model-00169-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
pytorch_model-00267-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
pytorch_model-00314-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
pytorch_model-00050-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
pytorch_model-00160-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
pytorch_model-00197-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
pytorch_model-00307-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
pytorch_model-00234-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
pytorch_model-00242-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
pytorch_model-00243-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
pytorch_model-00275-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
pytorch_model-00063-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
pytorch_model-00170-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
pytorch_model-00200-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
pytorch_model-00219-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
pytorch_model-00297-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
pytorch_model-00330-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
pytorch_model-00360-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
pytorch_model-00139-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
pytorch_model-00174-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
pytorch_model-00194-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
pytorch_model-00268-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
pytorch_model-00146-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
pytorch_model-00214-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
pytorch_model-00089-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
pytorch_model-00132-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
pytorch_model-00300-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
pytorch_model-00310-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
pytorch_model-00016-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
pytorch_model-00086-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
pytorch_model-00111-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
pytorch_model-00295-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
pytorch_model-00276-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
pytorch_model-00353-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
pytorch_model-00181-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
pytorch_model-00208-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
pytorch_model-00220-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
pytorch_model-00233-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
pytorch_model-00106-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
pytorch_model-00364-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
pytorch_model-00083-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
pytorch_model-00127-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
pytorch_model-00066-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
pytorch_model-00091-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
pytorch_model-00123-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
pytorch_model-00124-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
pytorch_model-00182-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
pytorch_model-00217-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
pytorch_model-00249-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
pytorch_model-00286-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
pytorch_model-00009-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
pytorch_model-00036-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
pytorch_model-00055-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
pytorch_model-00119-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
pytorch_model-00345-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
pytorch_model-00287-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
pytorch_model-00005-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
pytorch_model-00059-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
pytorch_model-00069-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
pytorch_model-00110-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
pytorch_model-00172-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
pytorch_model-00216-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
pytorch_model-00228-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
pytorch_model-00236-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
pytorch_model-00026-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
pytorch_model-00071-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 164 |
+
pytorch_model-00104-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 165 |
+
pytorch_model-00150-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 166 |
+
pytorch_model-00271-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 167 |
+
pytorch_model-00348-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 168 |
+
pytorch_model-00107-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 169 |
+
pytorch_model-00108-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 170 |
+
pytorch_model-00227-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 171 |
+
pytorch_model-00237-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 172 |
+
pytorch_model-00012-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 173 |
+
pytorch_model-00015-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 174 |
+
pytorch_model-00043-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 175 |
+
pytorch_model-00088-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 176 |
+
pytorch_model-00292-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 177 |
+
pytorch_model-00347-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 178 |
+
pytorch_model-00274-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 179 |
+
pytorch_model-00018-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 180 |
+
pytorch_model-00072-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 181 |
+
pytorch_model-00101-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 182 |
+
pytorch_model-00238-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 183 |
+
pytorch_model-00129-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 184 |
+
pytorch_model-00140-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 185 |
+
pytorch_model-00161-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 186 |
+
pytorch_model-00316-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 187 |
+
pytorch_model-00014-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 188 |
+
pytorch_model-00025-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 189 |
+
pytorch_model-00053-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 190 |
+
pytorch_model-00075-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 191 |
+
pytorch_model-00320-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 192 |
+
pytorch_model-00354-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 193 |
+
pytorch_model-00116-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 194 |
+
pytorch_model-00117-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 195 |
+
pytorch_model-00328-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 196 |
+
pytorch_model-00342-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 197 |
+
pytorch_model-00261-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 198 |
+
pytorch_model-00046-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 199 |
+
pytorch_model-00145-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 200 |
+
pytorch_model-00188-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 201 |
+
pytorch_model-00212-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 202 |
+
pytorch_model-00147-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 203 |
+
pytorch_model-00285-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 204 |
+
pytorch_model-00319-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 205 |
+
pytorch_model-00337-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 206 |
+
pytorch_model-00027-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 207 |
+
pytorch_model-00034-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 208 |
+
pytorch_model-00103-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 209 |
+
pytorch_model-00115-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 210 |
+
pytorch_model-00207-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 211 |
+
pytorch_model-00298-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 212 |
+
pytorch_model-00341-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 213 |
+
pytorch_model-00350-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 214 |
+
pytorch_model-00077-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 215 |
+
pytorch_model-00109-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 216 |
+
pytorch_model-00175-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 217 |
+
pytorch_model-00178-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 218 |
+
pytorch_model-00239-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 219 |
+
pytorch_model-00245-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 220 |
+
pytorch_model-00250-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 221 |
+
pytorch_model-00334-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 222 |
+
pytorch_model-00023-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 223 |
+
pytorch_model-00065-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 224 |
+
pytorch_model-00099-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 225 |
+
pytorch_model-00198-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 226 |
+
pytorch_model-00356-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 227 |
+
pytorch_model-00187-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 228 |
+
pytorch_model-00211-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 229 |
+
pytorch_model-00253-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 230 |
+
pytorch_model-00013-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 231 |
+
pytorch_model-00138-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 232 |
+
pytorch_model-00143-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 233 |
+
pytorch_model-00152-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 234 |
+
pytorch_model-00322-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 235 |
+
pytorch_model-00351-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 236 |
+
pytorch_model-00052-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 237 |
+
pytorch_model-00154-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 238 |
+
pytorch_model-00155-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 239 |
+
pytorch_model-00246-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 240 |
+
pytorch_model-00290-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 241 |
+
pytorch_model-00064-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 242 |
+
pytorch_model-00098-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 243 |
+
pytorch_model-00162-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 244 |
+
pytorch_model-00265-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 245 |
+
pytorch_model-00177-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 246 |
+
pytorch_model-00232-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 247 |
+
pytorch_model-00038-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 248 |
+
pytorch_model-00048-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 249 |
+
pytorch_model-00141-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 250 |
+
pytorch_model-00166-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 251 |
+
pytorch_model-00193-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 252 |
+
pytorch_model-00263-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 253 |
+
pytorch_model-00273-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 254 |
+
pytorch_model-00045-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 255 |
+
pytorch_model-00094-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 256 |
+
pytorch_model-00135-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 257 |
+
pytorch_model-00167-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 258 |
+
pytorch_model-00191-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 259 |
+
pytorch_model-00231-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 260 |
+
pytorch_model-00264-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 261 |
+
pytorch_model-00277-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 262 |
+
pytorch_model-00022-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 263 |
+
pytorch_model-00074-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 264 |
+
pytorch_model-00078-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 265 |
+
pytorch_model-00114-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 266 |
+
pytorch_model-00280-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 267 |
+
pytorch_model-00343-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 268 |
+
pytorch_model-00304-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 269 |
+
pytorch_model-00126-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 270 |
+
pytorch_model-00149-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 271 |
+
pytorch_model-00184-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 272 |
+
pytorch_model-00240-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 273 |
+
pytorch_model-00049-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 274 |
+
pytorch_model-00168-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 275 |
+
pytorch_model-00266-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 276 |
+
pytorch_model-00294-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 277 |
+
pytorch_model-00308-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 278 |
+
pytorch_model-00352-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 279 |
+
pytorch_model-00079-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 280 |
+
pytorch_model-00090-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 281 |
+
pytorch_model-00153-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 282 |
+
pytorch_model-00225-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 283 |
+
pytorch_model-00355-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 284 |
+
pytorch_model-00340-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 285 |
+
pytorch_model-00007-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 286 |
+
pytorch_model-00040-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 287 |
+
pytorch_model-00042-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 288 |
+
pytorch_model-00112-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 289 |
+
pytorch_model-00148-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 290 |
+
pytorch_model-00262-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 291 |
+
pytorch_model-00309-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 292 |
+
pytorch_model-00303-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 293 |
+
pytorch_model-00028-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 294 |
+
pytorch_model-00092-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 295 |
+
pytorch_model-00102-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 296 |
+
pytorch_model-00165-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 297 |
+
pytorch_model-00054-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 298 |
+
pytorch_model-00190-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 299 |
+
pytorch_model-00325-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 300 |
+
pytorch_model-00118-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 301 |
+
pytorch_model-00144-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 302 |
+
pytorch_model-00279-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 303 |
+
pytorch_model-00301-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 304 |
+
pytorch_model-00134-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 305 |
+
pytorch_model-00218-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 306 |
+
pytorch_model-00327-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 307 |
+
pytorch_model-00332-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 308 |
+
pytorch_model-00002-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 309 |
+
pytorch_model-00004-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 310 |
+
pytorch_model-00085-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 311 |
+
pytorch_model-00095-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 312 |
+
pytorch_model-00362-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 313 |
+
pytorch_model-00209-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 314 |
+
pytorch_model-00256-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 315 |
+
pytorch_model-00281-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 316 |
+
pytorch_model-00349-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 317 |
+
pytorch_model-00030-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 318 |
+
pytorch_model-00035-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 319 |
+
pytorch_model-00039-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 320 |
+
pytorch_model-00192-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 321 |
+
pytorch_model-00312-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 322 |
+
pytorch_model-00338-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 323 |
+
pytorch_model-00189-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 324 |
+
pytorch_model-00204-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 325 |
+
pytorch_model-00213-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 326 |
+
pytorch_model-00306-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 327 |
+
pytorch_model-00248-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 328 |
+
pytorch_model-00272-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 329 |
+
pytorch_model-00044-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 330 |
+
pytorch_model-00137-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 331 |
+
pytorch_model-00201-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 332 |
+
pytorch_model-00205-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 333 |
+
pytorch_model-00229-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 334 |
+
pytorch_model-00259-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 335 |
+
pytorch_model-00269-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 336 |
+
pytorch_model-00093-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 337 |
+
pytorch_model-00100-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 338 |
+
pytorch_model-00159-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 339 |
+
pytorch_model-00196-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 340 |
+
pytorch_model-00357-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 341 |
+
pytorch_model-00020-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 342 |
+
pytorch_model-00061-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 343 |
+
pytorch_model-00087-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 344 |
+
pytorch_model-00288-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 345 |
+
pytorch_model-00289-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 346 |
+
pytorch_model-00346-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 347 |
+
pytorch_model-00060-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 348 |
+
pytorch_model-00131-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 349 |
+
pytorch_model-00171-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 350 |
+
pytorch_model-00226-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 351 |
+
pytorch_model-00326-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 352 |
+
pytorch_model-00062-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 353 |
+
pytorch_model-00235-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 354 |
+
pytorch_model-00282-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 355 |
+
pytorch_model-00296-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 356 |
+
pytorch_model-00032-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 357 |
+
pytorch_model-00215-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 358 |
+
pytorch_model-00363-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 359 |
+
pytorch_model-00202-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 360 |
+
pytorch_model-00221-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 361 |
+
pytorch_model-00284-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 362 |
+
pytorch_model-00311-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 363 |
+
pytorch_model-00047-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 364 |
+
pytorch_model-00157-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 365 |
+
pytorch_model-00164-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 366 |
+
pytorch_model-00176-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 367 |
+
pytorch_model-00361-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 368 |
+
pytorch_model-00302-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 369 |
+
pytorch_model-00180-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 370 |
+
pytorch_model-00206-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 371 |
+
pytorch_model-00241-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 372 |
+
pytorch_model-00251-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 373 |
+
pytorch_model-00031-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 374 |
+
pytorch_model-00068-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 375 |
+
pytorch_model-00179-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 376 |
+
pytorch_model-00344-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 377 |
+
pytorch_model-00278-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 378 |
+
pytorch_model-00096-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 379 |
+
pytorch_model-00121-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 380 |
+
pytorch_model-00142-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 381 |
+
pytorch_model-00258-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 382 |
+
pytorch_model-00041-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 383 |
+
pytorch_model-00186-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 384 |
+
pytorch_model-00333-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 385 |
+
pytorch_model-00001-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 386 |
+
pytorch_model-00021-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 387 |
+
pytorch_model-00024-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 388 |
+
pytorch_model-00029-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 389 |
+
pytorch_model-00073-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 390 |
+
pytorch_model-00097-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 391 |
+
pytorch_model-00291-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 392 |
+
pytorch_model-00195-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 393 |
+
pytorch_model-00252-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 394 |
+
pytorch_model-00318-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 395 |
+
pytorch_model-00076-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 396 |
+
pytorch_model-00082-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 397 |
+
pytorch_model-00130-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 398 |
+
pytorch_model-00254-of-00364.bin filter=lfs diff=lfs merge=lfs -text
|
| 399 |
+
pytorch_model.bin.index.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_router_probs": false,
|
| 3 |
+
"d_ff": 6144,
|
| 4 |
+
"d_kv": 64,
|
| 5 |
+
"d_model": 2080,
|
| 6 |
+
"decoder_sparse_step": 0,
|
| 7 |
+
"dense_act_fn": "relu",
|
| 8 |
+
"dropout_rate": 0.1,
|
| 9 |
+
"encoder_sparse_step": 1,
|
| 10 |
+
"eos_token_id": 1,
|
| 11 |
+
"expert_capacity": 64,
|
| 12 |
+
"feed_forward_proj": "relu",
|
| 13 |
+
"initializer_factor": 1.0,
|
| 14 |
+
"is_encoder_decoder": true,
|
| 15 |
+
"is_full_sparse": true,
|
| 16 |
+
"is_gated_act": false,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "switch_transformers",
|
| 19 |
+
"num_decoder_layers": 12,
|
| 20 |
+
"num_experts": 2048,
|
| 21 |
+
"num_heads": 30,
|
| 22 |
+
"num_layers": 15,
|
| 23 |
+
"num_sparse_decoder_layers": 15,
|
| 24 |
+
"num_sparse_encoder_layers": 15,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"router_aux_loss_coef": 0.001,
|
| 29 |
+
"router_bias": false,
|
| 30 |
+
"router_dtype": "float32",
|
| 31 |
+
"router_ignore_padding_tokens": false,
|
| 32 |
+
"router_jitter_noise": 0.01,
|
| 33 |
+
"router_type": "tokens_masked",
|
| 34 |
+
"router_z_loss_coef": 0.001,
|
| 35 |
+
"transformers_version": "4.25.0.dev0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 32128
|
| 38 |
+
}
|