Update config.json
Browse files- config.json +0 -76
config.json
CHANGED
|
@@ -10,85 +10,9 @@
|
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 11008,
|
| 13 |
-
"layer_types": [
|
| 14 |
-
"full_attention",
|
| 15 |
-
"full_attention",
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention"
|
| 50 |
-
],
|
| 51 |
"max_position_embeddings": 65536,
|
| 52 |
"model_type": "smollm3",
|
| 53 |
"no_rope_layer_interval": 4,
|
| 54 |
-
"no_rope_layers": [
|
| 55 |
-
1,
|
| 56 |
-
1,
|
| 57 |
-
1,
|
| 58 |
-
0,
|
| 59 |
-
1,
|
| 60 |
-
1,
|
| 61 |
-
1,
|
| 62 |
-
0,
|
| 63 |
-
1,
|
| 64 |
-
1,
|
| 65 |
-
1,
|
| 66 |
-
0,
|
| 67 |
-
1,
|
| 68 |
-
1,
|
| 69 |
-
1,
|
| 70 |
-
0,
|
| 71 |
-
1,
|
| 72 |
-
1,
|
| 73 |
-
1,
|
| 74 |
-
0,
|
| 75 |
-
1,
|
| 76 |
-
1,
|
| 77 |
-
1,
|
| 78 |
-
0,
|
| 79 |
-
1,
|
| 80 |
-
1,
|
| 81 |
-
1,
|
| 82 |
-
0,
|
| 83 |
-
1,
|
| 84 |
-
1,
|
| 85 |
-
1,
|
| 86 |
-
0,
|
| 87 |
-
1,
|
| 88 |
-
1,
|
| 89 |
-
1,
|
| 90 |
-
0
|
| 91 |
-
],
|
| 92 |
"num_attention_heads": 16,
|
| 93 |
"num_hidden_layers": 36,
|
| 94 |
"num_key_value_heads": 4,
|
|
|
|
| 10 |
"hidden_size": 2048,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 11008,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"max_position_embeddings": 65536,
|
| 14 |
"model_type": "smollm3",
|
| 15 |
"no_rope_layer_interval": 4,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"num_attention_heads": 16,
|
| 17 |
"num_hidden_layers": 36,
|
| 18 |
"num_key_value_heads": 4,
|