songrunhe commited on
Commit
5d538f2
·
verified ·
1 Parent(s): 530dd97

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +12 -2
README.md CHANGED
@@ -29,15 +29,25 @@ All models in the series achieve **GLUE benchmark scores that surpass standard B
29
 
30
  ## How to Get Started with the Model
31
 
 
 
 
 
 
 
 
 
 
32
  ```python
33
  from transformers import AutoTokenizer, AutoModel
 
34
 
35
  tokenizer = AutoTokenizer.from_pretrained("manelalab/chrono-bert-v1-19991231")
36
- model = AutoModel.from_pretrained("manelalab/chrono-bert-v1-19991231")
37
 
38
  text = "You've gotta be very careful not to mess with the space-time continuum. -- Dr. Brown, Back to the Future"
39
 
40
- inputs = tokenizer(text, return_tensors="pt")
41
  outputs = model(**inputs)
42
  ```
43
 
 
29
 
30
  ## How to Get Started with the Model
31
 
32
+ The model is compatible with the `transformers` library starting from v4.48.0:
33
+
34
+ ```sh
35
+ pip install -U transformers>=4.48.0
36
+ pip install flash-attn
37
+ ```
38
+
39
+ Here is an example code of using the model:
40
+
41
  ```python
42
  from transformers import AutoTokenizer, AutoModel
43
+ device = 'cuda:0'
44
 
45
  tokenizer = AutoTokenizer.from_pretrained("manelalab/chrono-bert-v1-19991231")
46
+ model = AutoModel.from_pretrained("manelalab/chrono-bert-v1-19991231").to(device)
47
 
48
  text = "You've gotta be very careful not to mess with the space-time continuum. -- Dr. Brown, Back to the Future"
49
 
50
+ inputs = tokenizer(text, return_tensors="pt").to(device)
51
  outputs = model(**inputs)
52
  ```
53