Trim config to runtime essentials
Browse files- config.json +11 -66
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "2B",
|
| 3 |
"data": {
|
| 4 |
"channels": 34,
|
| 5 |
"text_vocab_size": 49280,
|
|
@@ -13,38 +12,10 @@
|
|
| 13 |
"action_pad_token_id": 0,
|
| 14 |
"action_new_word_token_id": 1,
|
| 15 |
"delay_pattern": [
|
| 16 |
-
16,
|
| 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 |
-
18
|
| 48 |
],
|
| 49 |
"first_word_min_start": 3,
|
| 50 |
"max_pad": 8,
|
|
@@ -78,42 +49,16 @@
|
|
| 78 |
"dropout": 0.0,
|
| 79 |
"rope_min_timescale": 1,
|
| 80 |
"rope_max_timescale": 10000.0,
|
| 81 |
-
"normalization_layer_epsilon":
|
| 82 |
},
|
| 83 |
"runtime": {
|
| 84 |
"weights_schedule": [
|
| 85 |
-
0,
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
1,
|
| 91 |
-
2,
|
| 92 |
-
2,
|
| 93 |
-
2,
|
| 94 |
-
2,
|
| 95 |
-
2,
|
| 96 |
-
2,
|
| 97 |
-
2,
|
| 98 |
-
2,
|
| 99 |
-
3,
|
| 100 |
-
3,
|
| 101 |
-
3,
|
| 102 |
-
3,
|
| 103 |
-
3,
|
| 104 |
-
3,
|
| 105 |
-
3,
|
| 106 |
-
3,
|
| 107 |
-
4,
|
| 108 |
-
4,
|
| 109 |
-
4,
|
| 110 |
-
4,
|
| 111 |
-
4,
|
| 112 |
-
4,
|
| 113 |
-
4,
|
| 114 |
-
4,
|
| 115 |
-
4
|
| 116 |
],
|
| 117 |
"max_context_steps": 1500
|
| 118 |
}
|
| 119 |
-
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"data": {
|
| 3 |
"channels": 34,
|
| 4 |
"text_vocab_size": 49280,
|
|
|
|
| 12 |
"action_pad_token_id": 0,
|
| 13 |
"action_new_word_token_id": 1,
|
| 14 |
"delay_pattern": [
|
| 15 |
+
16, 18, 18, 18, 18, 18, 18, 18,
|
| 16 |
+
18, 18, 18, 18, 18, 18, 18, 18,
|
| 17 |
+
18, 18, 18, 18, 18, 18, 18, 18,
|
| 18 |
+
18, 18, 18, 18, 18, 18, 18, 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
],
|
| 20 |
"first_word_min_start": 3,
|
| 21 |
"max_pad": 8,
|
|
|
|
| 49 |
"dropout": 0.0,
|
| 50 |
"rope_min_timescale": 1,
|
| 51 |
"rope_max_timescale": 10000.0,
|
| 52 |
+
"normalization_layer_epsilon": 0.000001
|
| 53 |
},
|
| 54 |
"runtime": {
|
| 55 |
"weights_schedule": [
|
| 56 |
+
0, 0,
|
| 57 |
+
1, 1, 1, 1,
|
| 58 |
+
2, 2, 2, 2, 2, 2, 2, 2,
|
| 59 |
+
3, 3, 3, 3, 3, 3, 3, 3,
|
| 60 |
+
4, 4, 4, 4, 4, 4, 4, 4, 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
],
|
| 62 |
"max_context_steps": 1500
|
| 63 |
}
|
| 64 |
+
}
|