jacobfulano commited on
Commit
6fccab2
1 Parent(s): 82a6d46

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -7,7 +7,7 @@ language:
7
  inference: false
8
  ---
9
 
10
- # MosaicBERT: mosaic-bert-base-seqlen-512 Pretrained Model
11
 
12
  MosaicBERT-Base is a new BERT architecture and training recipe optimized for fast pretraining.
13
  MosaicBERT trains faster and achieves higher pretraining and finetuning accuracy when benchmarked against
@@ -42,7 +42,7 @@ April 2023
42
 
43
  ```python
44
  from transformers import AutoModelForMaskedLM
45
- mlm = AutoModelForMaskedLM.from_pretrained('mosaicml/mosaic-bert-base', trust_remote_code=True)
46
  ```
47
 
48
  The tokenizer for this model is simply the Hugging Face `bert-base-uncased` tokenizer.
@@ -58,7 +58,7 @@ To use this model directly for masked language modeling, use `pipeline`:
58
  from transformers import AutoModelForMaskedLM, BertTokenizer, pipeline
59
 
60
  tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
61
- mlm = AutoModelForMaskedLM.from_pretrained('mosaicml/mosaic-bert-base', trust_remote_code=True)
62
 
63
  classifier = pipeline('fill-mask', model=mlm, tokenizer=tokenizer)
64
 
@@ -75,7 +75,7 @@ This model requires that `trust_remote_code=True` be passed to the `from_pretrai
75
 
76
  ```python
77
  mlm = AutoModelForMaskedLM.from_pretrained(
78
- 'mosaicml/mosaic-bert-base',
79
  trust_remote_code=True,
80
  revision='24512df',
81
  )
 
7
  inference: false
8
  ---
9
 
10
+ # MosaicBERT: mosaic-bert-base-seqlen-256 Pretrained Model
11
 
12
  MosaicBERT-Base is a new BERT architecture and training recipe optimized for fast pretraining.
13
  MosaicBERT trains faster and achieves higher pretraining and finetuning accuracy when benchmarked against
 
42
 
43
  ```python
44
  from transformers import AutoModelForMaskedLM
45
+ mlm = AutoModelForMaskedLM.from_pretrained('mosaicml/mosaic-bert-base-seqlen-256', trust_remote_code=True)
46
  ```
47
 
48
  The tokenizer for this model is simply the Hugging Face `bert-base-uncased` tokenizer.
 
58
  from transformers import AutoModelForMaskedLM, BertTokenizer, pipeline
59
 
60
  tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
61
+ mlm = AutoModelForMaskedLM.from_pretrained('mosaicml/mosaic-bert-base-seqlen-256', trust_remote_code=True)
62
 
63
  classifier = pipeline('fill-mask', model=mlm, tokenizer=tokenizer)
64
 
 
75
 
76
  ```python
77
  mlm = AutoModelForMaskedLM.from_pretrained(
78
+ 'mosaicml/mosaic-bert-base-seqlen-256',
79
  trust_remote_code=True,
80
  revision='24512df',
81
  )