Lancelot53
commited on
Upload BertForMaskedLM
Browse files- config.json +31 -31
- generation_config.json +5 -5
- pytorch_model.bin +1 -1
config.json
CHANGED
@@ -1,31 +1,31 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"alibi_starting_size": 128,
|
4 |
-
"architectures": [
|
5 |
-
"BertForMaskedLM"
|
6 |
-
],
|
7 |
-
"attention_probs_dropout_prob": 0.1,
|
8 |
-
"auto_map": {
|
9 |
-
"AutoConfig": "configuration_bert.BertConfig",
|
10 |
-
"AutoModelForMaskedLM": "bert_layers.BertForMaskedLM"
|
11 |
-
},
|
12 |
-
"classifier_dropout": null,
|
13 |
-
"gradient_checkpointing": false,
|
14 |
-
"hidden_act": "gelu",
|
15 |
-
"hidden_dropout_prob": 0.1,
|
16 |
-
"hidden_size": 768,
|
17 |
-
"initializer_range": 0.02,
|
18 |
-
"intermediate_size": 3072,
|
19 |
-
"layer_norm_eps": 1e-12,
|
20 |
-
"max_position_embeddings": 128,
|
21 |
-
"model_type": "bert",
|
22 |
-
"num_attention_heads": 12,
|
23 |
-
"num_hidden_layers": 12,
|
24 |
-
"pad_token_id": 0,
|
25 |
-
"position_embedding_type": "absolute",
|
26 |
-
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
-
"type_vocab_size": 2,
|
29 |
-
"use_cache": true,
|
30 |
-
"vocab_size": 4096
|
31 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "temp_bpe_nuc_157k",
|
3 |
+
"alibi_starting_size": 128,
|
4 |
+
"architectures": [
|
5 |
+
"BertForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_bert.BertConfig",
|
10 |
+
"AutoModelForMaskedLM": "bert_layers.BertForMaskedLM"
|
11 |
+
},
|
12 |
+
"classifier_dropout": null,
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 128,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.29.0",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 4096
|
31 |
+
}
|
generation_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"pad_token_id": 0,
|
4 |
-
"transformers_version": "4.
|
5 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.29.0"
|
5 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 465958186
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:207a6f7e57fbfd6a57436d5c7b52890b693491460bd4883b3c083f182bbc76aa
|
3 |
size 465958186
|