dqnguyen commited on
Commit
667b559
1 Parent(s): 7015a74

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -35
README.md CHANGED
@@ -18,38 +18,3 @@ The general architecture and experimental results of PhoBERT can be found in our
18
 
19
  For further information or requests, please go to [PhoBERT's homepage](https://github.com/VinAIResearch/PhoBERT)!
20
 
21
- ### Installation <a name="install2"></a>
22
- - Python 3.6+, and PyTorch 1.1.0+ (or TensorFlow 2.0+)
23
- - Install `transformers`:
24
- - `git clone https://github.com/huggingface/transformers.git`
25
- - `cd transformers`
26
- - `pip3 install --upgrade .`
27
-
28
- ### Pre-trained models <a name="models2"></a>
29
-
30
- Model | #params | Arch. | Pre-training data
31
- ---|---|---|---
32
- `vinai/phobert-base` | 135M | base | 20GB of texts
33
- `vinai/phobert-large` | 370M | large | 20GB of texts
34
-
35
- ### Example usage <a name="usage2"></a>
36
-
37
- ```python
38
- import torch
39
- from transformers import AutoModel, AutoTokenizer
40
-
41
- phobert = AutoModel.from_pretrained("vinai/phobert-base")
42
- tokenizer = AutoTokenizer.from_pretrained("vinai/phobert-base")
43
-
44
- # INPUT TEXT MUST BE ALREADY WORD-SEGMENTED!
45
- line = "Tôi là sinh_viên trường đại_học Công_nghệ ."
46
-
47
- input_ids = torch.tensor([tokenizer.encode(line)])
48
-
49
- with torch.no_grad():
50
- features = phobert(input_ids) # Models outputs are now tuples
51
-
52
- ## With TensorFlow 2.0+:
53
- # from transformers import TFAutoModel
54
- # phobert = TFAutoModel.from_pretrained("vinai/phobert-base")
55
- ```
 
18
 
19
  For further information or requests, please go to [PhoBERT's homepage](https://github.com/VinAIResearch/PhoBERT)!
20