egoriya commited on
Commit
3eef449
1 Parent(s): f168f1b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -1,11 +1,11 @@
1
  ---
2
  license: mit
3
  widget:
4
- - text: "привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]супер, вот только проснулся, у тебя как?"
5
  example_title: "Dialog example 1"
6
- - text: "привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]норм"
7
  example_title: "Dialog example 2"
8
- - text: "привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]норм, у тя как?"
9
  example_title: "Dialog example 3"
10
  ---
11
 
@@ -33,12 +33,11 @@ The performance of the model on validation split (dataset will be posted soon) (
33
  How to use:
34
 
35
  ```python
36
- pip install transformers
37
- from transformers import AutoTokenizer, AutoModelForSequenceClassification
38
  import torch
 
 
39
  tokenizer = AutoTokenizer.from_pretrained('tinkoff-ai/response-quality-classifier-base')
40
  model = AutoModelForSequenceClassification.from_pretrained('tinkoff-ai/response-quality-classifier-base')
41
- model.cuda()
42
  inputs = tokenizer('[CLS]привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]норм, у тя как?', max_length=128, add_special_tokens=False, return_tensors='pt')
43
  with torch.inference_mode():
44
  logits = model(**inputs).logits
 
1
  ---
2
  license: mit
3
  widget:
4
+ - text: "[CLS]привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]супер, вот только проснулся, у тебя как?"
5
  example_title: "Dialog example 1"
6
+ - text: "[CLS]привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]норм"
7
  example_title: "Dialog example 2"
8
+ - text: "[CLS]привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]норм, у тя как?"
9
  example_title: "Dialog example 3"
10
  ---
11
 
 
33
  How to use:
34
 
35
  ```python
 
 
36
  import torch
37
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
38
+
39
  tokenizer = AutoTokenizer.from_pretrained('tinkoff-ai/response-quality-classifier-base')
40
  model = AutoModelForSequenceClassification.from_pretrained('tinkoff-ai/response-quality-classifier-base')
 
41
  inputs = tokenizer('[CLS]привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]норм, у тя как?', max_length=128, add_special_tokens=False, return_tensors='pt')
42
  with torch.inference_mode():
43
  logits = model(**inputs).logits