Update README.md
Browse files
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-tiny')
|
40 |
model = AutoModelForSequenceClassification.from_pretrained('tinkoff-ai/response-quality-classifier-tiny')
|
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-tiny')
|
40 |
model = AutoModelForSequenceClassification.from_pretrained('tinkoff-ai/response-quality-classifier-tiny')
|
|
|
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
|