gchhablani commited on
Commit
a55593d
1 Parent(s): 9cf25b2

Add or Fix Model

Browse files
Files changed (2) hide show
  1. README.md +2 -2
  2. config.json +23 -23
README.md CHANGED
@@ -9,8 +9,8 @@ datasets:
9
  - bookcorpus
10
  - wikipedia
11
  ---
12
- # MultiBERTs Seed 0 Checkpoint 20k (uncased)
13
- Seed 0 intermediate checkpoint 20k MultiBERTs (pretrained BERT) model on English language using a masked language modeling (MLM) objective. It was introduced in
14
  [this paper](https://arxiv.org/pdf/2106.16163.pdf) and first released in
15
  [this repository](https://github.com/google-research/language/tree/master/language/multiberts). This model is uncased: it does not make a difference
16
  between english and English.
 
9
  - bookcorpus
10
  - wikipedia
11
  ---
12
+ # MultiBERTs Seed 1 Checkpoint 20k (uncased)
13
+ Seed 1 intermediate checkpoint 20k MultiBERTs (pretrained BERT) model on English language using a masked language modeling (MLM) objective. It was introduced in
14
  [this paper](https://arxiv.org/pdf/2106.16163.pdf) and first released in
15
  [this repository](https://github.com/google-research/language/tree/master/language/multiberts). This model is uncased: it does not make a difference
16
  between english and English.
config.json CHANGED
@@ -1,24 +1,24 @@
1
  {
2
- "architectures": [
3
- "BertForPreTraining"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "classifier_dropout": null,
7
- "hidden_act": "gelu",
8
- "hidden_dropout_prob": 0.1,
9
- "hidden_size": 768,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 3072,
12
- "layer_norm_eps": 1e-12,
13
- "max_position_embeddings": 512,
14
- "model_type": "bert",
15
- "num_attention_heads": 12,
16
- "num_hidden_layers": 12,
17
- "pad_token_id": 0,
18
- "position_embedding_type": "absolute",
19
- "torch_dtype": "float32",
20
- "transformers_version": "4.11.0.dev0",
21
- "type_vocab_size": 2,
22
- "use_cache": true,
23
- "vocab_size": 30522
24
- }
 
1
  {
2
+ "architectures": [
3
+ "BertForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.11.0.dev0",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }