Fix runtime weights schedule for Dia2-1B
Browse files- config.json +64 -10
config.json
CHANGED
|
@@ -12,10 +12,38 @@
|
|
| 12 |
"action_pad_token_id": 0,
|
| 13 |
"action_new_word_token_id": 1,
|
| 14 |
"delay_pattern": [
|
| 15 |
-
16,
|
| 16 |
-
18,
|
| 17 |
-
18,
|
| 18 |
-
18,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
],
|
| 20 |
"first_word_min_start": 3,
|
| 21 |
"max_pad": 8,
|
|
@@ -49,15 +77,41 @@
|
|
| 49 |
"dropout": 0.0,
|
| 50 |
"rope_min_timescale": 1,
|
| 51 |
"rope_max_timescale": 10000.0,
|
| 52 |
-
"normalization_layer_epsilon":
|
| 53 |
},
|
| 54 |
"runtime": {
|
| 55 |
"weights_schedule": [
|
| 56 |
-
0,
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
],
|
| 62 |
"max_context_steps": 1500
|
| 63 |
}
|
|
|
|
| 12 |
"action_pad_token_id": 0,
|
| 13 |
"action_new_word_token_id": 1,
|
| 14 |
"delay_pattern": [
|
| 15 |
+
16,
|
| 16 |
+
18,
|
| 17 |
+
18,
|
| 18 |
+
18,
|
| 19 |
+
18,
|
| 20 |
+
18,
|
| 21 |
+
18,
|
| 22 |
+
18,
|
| 23 |
+
18,
|
| 24 |
+
18,
|
| 25 |
+
18,
|
| 26 |
+
18,
|
| 27 |
+
18,
|
| 28 |
+
18,
|
| 29 |
+
18,
|
| 30 |
+
18,
|
| 31 |
+
18,
|
| 32 |
+
18,
|
| 33 |
+
18,
|
| 34 |
+
18,
|
| 35 |
+
18,
|
| 36 |
+
18,
|
| 37 |
+
18,
|
| 38 |
+
18,
|
| 39 |
+
18,
|
| 40 |
+
18,
|
| 41 |
+
18,
|
| 42 |
+
18,
|
| 43 |
+
18,
|
| 44 |
+
18,
|
| 45 |
+
18,
|
| 46 |
+
18
|
| 47 |
],
|
| 48 |
"first_word_min_start": 3,
|
| 49 |
"max_pad": 8,
|
|
|
|
| 77 |
"dropout": 0.0,
|
| 78 |
"rope_min_timescale": 1,
|
| 79 |
"rope_max_timescale": 10000.0,
|
| 80 |
+
"normalization_layer_epsilon": 1e-06
|
| 81 |
},
|
| 82 |
"runtime": {
|
| 83 |
"weights_schedule": [
|
| 84 |
+
0,
|
| 85 |
+
0,
|
| 86 |
+
0,
|
| 87 |
+
0,
|
| 88 |
+
0,
|
| 89 |
+
0,
|
| 90 |
+
0,
|
| 91 |
+
0,
|
| 92 |
+
1,
|
| 93 |
+
1,
|
| 94 |
+
1,
|
| 95 |
+
1,
|
| 96 |
+
1,
|
| 97 |
+
1,
|
| 98 |
+
1,
|
| 99 |
+
1,
|
| 100 |
+
2,
|
| 101 |
+
2,
|
| 102 |
+
2,
|
| 103 |
+
2,
|
| 104 |
+
2,
|
| 105 |
+
2,
|
| 106 |
+
2,
|
| 107 |
+
2,
|
| 108 |
+
2,
|
| 109 |
+
2,
|
| 110 |
+
2,
|
| 111 |
+
2,
|
| 112 |
+
2,
|
| 113 |
+
2,
|
| 114 |
+
2
|
| 115 |
],
|
| 116 |
"max_context_steps": 1500
|
| 117 |
}
|