Update README.md
Browse files
README.md
CHANGED
@@ -19,11 +19,12 @@ The model is based on the [North-T5-NCC Large](https://huggingface.co/north/t5_l
|
|
19 |
- **Model type:** Language model restricted to classification
|
20 |
- **Language(s) (NLP):** Danish and Norwegian
|
21 |
- **License:** [More Information Needed]
|
22 |
-
- **Finetuned from model:** [
|
23 |
|
24 |
|
25 |
# Direct Use
|
26 |
-
|
|
|
27 |
|
28 |
|
29 |
# Bias, Risks, and Limitations
|
@@ -33,7 +34,8 @@ The model can be used directly to classify Danish and Norwegian social media pos
|
|
33 |
# Training Data
|
34 |
A collection of ~70k Norwegian and ~67k Danish social media posts have been manually annotated as 'attack' or 'not attack' by six individual coders. 5% of the posts have been annotated by more then one annotator, with the annotators in agreement for 83% of annotations.
|
35 |
|
36 |
-
|
|
|
37 |
|
38 |
# Evaluation
|
39 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
@@ -94,7 +96,7 @@ model = AutoModelForSeq2SeqLM.from_pretrained("ogtal/A-og-ttack2")
|
|
94 |
|
95 |
# Give sample text. The example is from a social media comment.
|
96 |
sample_text = "Velbekomme dit klamme usle løgnersvin!"
|
97 |
-
input_ids = tokenizer(
|
98 |
|
99 |
# Forward pass and print the output
|
100 |
outputs = model.generate(input_ids)
|
|
|
19 |
- **Model type:** Language model restricted to classification
|
20 |
- **Language(s) (NLP):** Danish and Norwegian
|
21 |
- **License:** [More Information Needed]
|
22 |
+
- **Finetuned from model:** [North-T5-NCC Large](https://huggingface.co/north/t5_large_NCC)
|
23 |
|
24 |
|
25 |
# Direct Use
|
26 |
+
This model can be used for classifying Danish and Norwegian social media posts or similar text.
|
27 |
+
|
28 |
|
29 |
|
30 |
# Bias, Risks, and Limitations
|
|
|
34 |
# Training Data
|
35 |
A collection of ~70k Norwegian and ~67k Danish social media posts have been manually annotated as 'attack' or 'not attack' by six individual coders. 5% of the posts have been annotated by more then one annotator, with the annotators in agreement for 83% of annotations.
|
36 |
|
37 |
+
[More information needed on the data split method and the training-validation-test split.]
|
38 |
+
|
39 |
|
40 |
# Evaluation
|
41 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
|
|
96 |
|
97 |
# Give sample text. The example is from a social media comment.
|
98 |
sample_text = "Velbekomme dit klamme usle løgnersvin!"
|
99 |
+
input_ids = tokenizer(sample_text, return_tensors="pt").input_ids
|
100 |
|
101 |
# Forward pass and print the output
|
102 |
outputs = model.generate(input_ids)
|