Instructions to use belrem/llm-prompt-intent-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use belrem/llm-prompt-intent-classifier with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("belrem/llm-prompt-intent-classifier") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Upload results.json with huggingface_hub
Browse files- results.json +98 -0
results.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Logistic Regression": {
|
| 3 |
+
"accuracy": 0.8218,
|
| 4 |
+
"f1_macro": 0.8222,
|
| 5 |
+
"f1_weighted": 0.8209,
|
| 6 |
+
"report": " precision recall f1-score support\n\n creative 0.78 0.89 0.83 45\ninformational 0.84 0.77 0.80 48\n task 0.80 0.89 0.85 37\n adversarial 0.87 0.75 0.80 44\n\n accuracy 0.82 174\n macro avg 0.82 0.83 0.82 174\n weighted avg 0.83 0.82 0.82 174\n",
|
| 7 |
+
"confusion_matrix": [
|
| 8 |
+
[
|
| 9 |
+
40,
|
| 10 |
+
2,
|
| 11 |
+
3,
|
| 12 |
+
0
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
3,
|
| 16 |
+
37,
|
| 17 |
+
5,
|
| 18 |
+
3
|
| 19 |
+
],
|
| 20 |
+
[
|
| 21 |
+
0,
|
| 22 |
+
2,
|
| 23 |
+
33,
|
| 24 |
+
2
|
| 25 |
+
],
|
| 26 |
+
[
|
| 27 |
+
8,
|
| 28 |
+
3,
|
| 29 |
+
0,
|
| 30 |
+
33
|
| 31 |
+
]
|
| 32 |
+
]
|
| 33 |
+
},
|
| 34 |
+
"Linear SVM": {
|
| 35 |
+
"accuracy": 0.7816,
|
| 36 |
+
"f1_macro": 0.7824,
|
| 37 |
+
"f1_weighted": 0.7816,
|
| 38 |
+
"report": " precision recall f1-score support\n\n creative 0.70 0.84 0.77 45\ninformational 0.84 0.75 0.79 48\n task 0.78 0.84 0.81 37\n adversarial 0.84 0.70 0.77 44\n\n accuracy 0.78 174\n macro avg 0.79 0.78 0.78 174\n weighted avg 0.79 0.78 0.78 174\n",
|
| 39 |
+
"confusion_matrix": [
|
| 40 |
+
[
|
| 41 |
+
38,
|
| 42 |
+
1,
|
| 43 |
+
5,
|
| 44 |
+
1
|
| 45 |
+
],
|
| 46 |
+
[
|
| 47 |
+
6,
|
| 48 |
+
36,
|
| 49 |
+
3,
|
| 50 |
+
3
|
| 51 |
+
],
|
| 52 |
+
[
|
| 53 |
+
1,
|
| 54 |
+
3,
|
| 55 |
+
31,
|
| 56 |
+
2
|
| 57 |
+
],
|
| 58 |
+
[
|
| 59 |
+
9,
|
| 60 |
+
3,
|
| 61 |
+
1,
|
| 62 |
+
31
|
| 63 |
+
]
|
| 64 |
+
]
|
| 65 |
+
},
|
| 66 |
+
"MLP": {
|
| 67 |
+
"accuracy": 0.8103,
|
| 68 |
+
"f1_macro": 0.809,
|
| 69 |
+
"f1_weighted": 0.81,
|
| 70 |
+
"report": " precision recall f1-score support\n\n creative 0.83 0.87 0.85 45\ninformational 0.75 0.85 0.80 48\n task 0.84 0.73 0.78 37\n adversarial 0.85 0.77 0.81 44\n\n accuracy 0.81 174\n macro avg 0.82 0.81 0.81 174\n weighted avg 0.81 0.81 0.81 174\n",
|
| 71 |
+
"confusion_matrix": [
|
| 72 |
+
[
|
| 73 |
+
39,
|
| 74 |
+
4,
|
| 75 |
+
2,
|
| 76 |
+
0
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
0,
|
| 80 |
+
41,
|
| 81 |
+
3,
|
| 82 |
+
4
|
| 83 |
+
],
|
| 84 |
+
[
|
| 85 |
+
1,
|
| 86 |
+
7,
|
| 87 |
+
27,
|
| 88 |
+
2
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
7,
|
| 92 |
+
3,
|
| 93 |
+
0,
|
| 94 |
+
34
|
| 95 |
+
]
|
| 96 |
+
]
|
| 97 |
+
}
|
| 98 |
+
}
|