gchhablani commited on
Commit
6449de2
1 Parent(s): 8b22170
Files changed (2) hide show
  1. README.md +3 -3
  2. config.json +23 -23
README.md CHANGED
@@ -8,8 +8,8 @@ datasets:
8
  - bookcorpus
9
  - wikipedia
10
  ---
11
- # MultiBERTs Seed 1300000 Checkpoint 1300k (uncased)
12
- Seed 1300000 intermediate checkpoint 1300k MultiBERTs (pretrained BERT) model on English language using a masked language modeling (MLM) objective. It was introduced in
13
  [this paper](https://arxiv.org/pdf/2106.16163.pdf) and first released in
14
  [this repository](https://github.com/google-research/language/tree/master/language/multiberts). This model is uncased: it does not make a difference
15
  between english and English.
@@ -46,7 +46,7 @@ Here is how to use this model to get the features of a given text in PyTorch:
46
  ```python
47
  from transformers import BertTokenizer, BertModel
48
  tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
49
- model = BertModel.from_pretrained("multiberts-seed-1300000-1300k")
50
  text = "Replace me by any text you'd like."
51
  encoded_input = tokenizer(text, return_tensors='pt')
52
  output = model(**encoded_input)
 
8
  - bookcorpus
9
  - wikipedia
10
  ---
11
+ # MultiBERTs Seed 0 Checkpoint 1300k (uncased)
12
+ Seed 0 intermediate checkoint 1300k MultiBERTs (pretrained BERT) model on English language using a masked language modeling (MLM) objective. It was introduced in
13
  [this paper](https://arxiv.org/pdf/2106.16163.pdf) and first released in
14
  [this repository](https://github.com/google-research/language/tree/master/language/multiberts). This model is uncased: it does not make a difference
15
  between english and English.
 
46
  ```python
47
  from transformers import BertTokenizer, BertModel
48
  tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
49
+ model = BertModel.from_pretrained("multiberts-seed-0-1300k")
50
  text = "Replace me by any text you'd like."
51
  encoded_input = tokenizer(text, return_tensors='pt')
52
  output = model(**encoded_input)
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
+ }