filipignijic
commited on
Commit
•
1ae21d6
1
Parent(s):
25fc10b
Upload ActivationsRobertaForMaskedLM
Browse files- config.json +28 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "c:\\Users\\Filip\\Documents\\School\\Delft\\Research project\\results\\upload\\BERT-PReLU",
|
3 |
+
"architectures": [
|
4 |
+
"ActivationsRobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"custom_activation": "prelu",
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 512,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1024,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 513,
|
18 |
+
"model_type": "activations_roberta",
|
19 |
+
"num_attention_heads": 4,
|
20 |
+
"num_hidden_layers": 2,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.26.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 10000
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8c7353823aeffa0d7a4382c355d352055bcffa1cdbf7fc73f350f504c72b72d
|
3 |
+
size 39482997
|