fix: Align layer_types with num_hidden_layers for transformers>=4.57.0
Browse files- config.json +1 -23
config.json
CHANGED
|
@@ -13,28 +13,6 @@
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 16,
|
| 15 |
"layer_types": [
|
| 16 |
-
"sliding_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"sliding_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"sliding_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"sliding_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"sliding_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"sliding_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"sliding_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"sliding_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"sliding_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"sliding_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"sliding_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
"sliding_attention",
|
| 39 |
"full_attention"
|
| 40 |
],
|
|
@@ -62,7 +40,7 @@
|
|
| 62 |
"swiglu_limit": 7.0,
|
| 63 |
"tie_word_embeddings": false,
|
| 64 |
"torch_dtype": "bfloat16",
|
| 65 |
-
"transformers_version": "4.
|
| 66 |
"use_cache": true,
|
| 67 |
"vocab_size": 201088
|
| 68 |
}
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 16,
|
| 15 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"sliding_attention",
|
| 17 |
"full_attention"
|
| 18 |
],
|
|
|
|
| 40 |
"swiglu_limit": 7.0,
|
| 41 |
"tie_word_embeddings": false,
|
| 42 |
"torch_dtype": "bfloat16",
|
| 43 |
+
"transformers_version": "4.57.6",
|
| 44 |
"use_cache": true,
|
| 45 |
"vocab_size": 201088
|
| 46 |
}
|