[doc]: update examples of usage the model
Browse files
README.md
CHANGED
@@ -73,10 +73,13 @@ We are pleased to achieve the following state of model calibration and high accc
|
|
73 |
|
74 |
**Pre-requirements**: \
|
75 |
Install *generated_text_detector* \
|
76 |
-
Run following command: ```pip install git+https://github.com/superannotateai/generated_text_detector.git@v1.
|
|
|
|
|
77 |
|
78 |
```python
|
79 |
from generated_text_detector.utils.model.roberta_classifier import RobertaClassifier
|
|
|
80 |
from transformers import AutoTokenizer
|
81 |
import torch.nn.functional as F
|
82 |
|
@@ -84,16 +87,20 @@ import torch.nn.functional as F
|
|
84 |
model = RobertaClassifier.from_pretrained("SuperAnnotate/ai-detector")
|
85 |
tokenizer = AutoTokenizer.from_pretrained("SuperAnnotate/ai-detector")
|
86 |
|
|
|
|
|
87 |
text_example = "It's not uncommon for people to develop allergies or intolerances to certain foods as they get older. It's possible that you have always had a sensitivity to lactose (the sugar found in milk and other dairy products), but it only recently became a problem for you. This can happen because our bodies can change over time and become more or less able to tolerate certain things. It's also possible that you have developed an allergy or intolerance to something else that is causing your symptoms, such as a food additive or preservative. In any case, it's important to talk to a doctor if you are experiencing new allergy or intolerance symptoms, so they can help determine the cause and recommend treatment."
|
88 |
|
|
|
|
|
89 |
tokens = tokenizer.encode_plus(
|
90 |
-
text_example,
|
91 |
-
add_special_tokens=True,
|
92 |
-
max_length=512,
|
93 |
-
padding='longest',
|
94 |
-
truncation=True,
|
95 |
-
return_token_type_ids=True,
|
96 |
-
return_tensors="pt"
|
97 |
)
|
98 |
|
99 |
_, logits = model(**tokens)
|
@@ -103,6 +110,25 @@ proba = F.sigmoid(logits).squeeze(1).item()
|
|
103 |
print(proba)
|
104 |
```
|
105 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
## Training Detailes
|
107 |
|
108 |
A custom architecture was chosen for its ability to perform binary classification while providing a single model output, as well as for its customizable settings for smoothing integrated into the loss function.
|
|
|
73 |
|
74 |
**Pre-requirements**: \
|
75 |
Install *generated_text_detector* \
|
76 |
+
Run following command: ```pip install git+https://github.com/superannotateai/generated_text_detector.git@v1.1.0```
|
77 |
+
|
78 |
+
### Native Usage
|
79 |
|
80 |
```python
|
81 |
from generated_text_detector.utils.model.roberta_classifier import RobertaClassifier
|
82 |
+
from generated_text_detector.utils.preprocessing import preprocessing_text
|
83 |
from transformers import AutoTokenizer
|
84 |
import torch.nn.functional as F
|
85 |
|
|
|
87 |
model = RobertaClassifier.from_pretrained("SuperAnnotate/ai-detector")
|
88 |
tokenizer = AutoTokenizer.from_pretrained("SuperAnnotate/ai-detector")
|
89 |
|
90 |
+
model.eval()
|
91 |
+
|
92 |
text_example = "It's not uncommon for people to develop allergies or intolerances to certain foods as they get older. It's possible that you have always had a sensitivity to lactose (the sugar found in milk and other dairy products), but it only recently became a problem for you. This can happen because our bodies can change over time and become more or less able to tolerate certain things. It's also possible that you have developed an allergy or intolerance to something else that is causing your symptoms, such as a food additive or preservative. In any case, it's important to talk to a doctor if you are experiencing new allergy or intolerance symptoms, so they can help determine the cause and recommend treatment."
|
93 |
|
94 |
+
text_example = preprocessing_text(text_example)
|
95 |
+
|
96 |
tokens = tokenizer.encode_plus(
|
97 |
+
text_example,
|
98 |
+
add_special_tokens=True,
|
99 |
+
max_length=512,
|
100 |
+
padding='longest',
|
101 |
+
truncation=True,
|
102 |
+
return_token_type_ids=True,
|
103 |
+
return_tensors="pt"
|
104 |
)
|
105 |
|
106 |
_, logits = model(**tokens)
|
|
|
110 |
print(proba)
|
111 |
```
|
112 |
|
113 |
+
### Usage in Detector Wrapper
|
114 |
+
|
115 |
+
```python
|
116 |
+
from generated_text_detector.utils.text_detector import GeneratedTextDetector
|
117 |
+
|
118 |
+
|
119 |
+
detector = GeneratedTextDetector(
|
120 |
+
"SuperAnnotate/ai-detector",
|
121 |
+
device="cuda",
|
122 |
+
preprocessing=True
|
123 |
+
)
|
124 |
+
|
125 |
+
text_example = "It's not uncommon for people to develop allergies or intolerances to certain foods as they get older. It's possible that you have always had a sensitivity to lactose (the sugar found in milk and other dairy products), but it only recently became a problem for you. This can happen because our bodies can change over time and become more or less able to tolerate certain things. It's also possible that you have developed an allergy or intolerance to something else that is causing your symptoms, such as a food additive or preservative. In any case, it's important to talk to a doctor if you are experiencing new allergy or intolerance symptoms, so they can help determine the cause and recommend treatment."
|
126 |
+
|
127 |
+
res = detector.detect_report(text_example)
|
128 |
+
|
129 |
+
print(res)
|
130 |
+
```
|
131 |
+
|
132 |
## Training Detailes
|
133 |
|
134 |
A custom architecture was chosen for its ability to perform binary classification while providing a single model output, as well as for its customizable settings for smoothing integrated into the loss function.
|