Update config.json
Browse files- config.json +37 -21
config.json
CHANGED
|
@@ -1,25 +1,41 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"random"
|
| 4 |
],
|
| 5 |
+
"hidden_act": "gelu-1000",
|
| 6 |
+
"hidden_dropout_prob": 1000,
|
| 7 |
+
"hidden_size": 1000,
|
| 8 |
+
"initializer_range": 1000,
|
| 9 |
+
"intermediate_size": 1000,
|
| 10 |
+
"layer_norm_eps": 1000,
|
| 11 |
+
"max_position_embeddings": 1000,
|
| 12 |
+
"model_type": "llama",
|
| 13 |
+
"num_attention_heads": 1000,
|
| 14 |
+
"num_hidden_layers": 1000,
|
| 15 |
+
"vocab_size": 1124,
|
| 16 |
+
"transformers_config": {
|
| 17 |
+
"architectures": [
|
| 18 |
+
"BertLMHeadModel"
|
| 19 |
+
],
|
| 20 |
+
"attention_probs_dropout_prob": 0.1,
|
| 21 |
+
"classifier_dropout": null,
|
| 22 |
+
"gradient_checkpointing": false,
|
| 23 |
+
"hidden_act": "gelu",
|
| 24 |
+
"hidden_dropout_prob": 0.1,
|
| 25 |
+
"hidden_size": 32,
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 37,
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "bert",
|
| 31 |
+
"num_attention_heads": 4,
|
| 32 |
+
"num_hidden_layers": 5,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"position_embedding_type": "absolute",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.53.0.dev0",
|
| 37 |
+
"type_vocab_size": 16,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 1124
|
| 40 |
+
}
|
| 41 |
}
|