saattrupdan
commited on
Commit
•
2930517
1
Parent(s):
17adc9b
Update README.md
Browse files
README.md
CHANGED
@@ -68,6 +68,12 @@ The following is the Micro-F1 NER performance on Scandinavian NER test datasets,
|
|
68 |
| Maltehb/-l-ctra-danish-electra-small-uncased-ner-dane | 70.41 ± 1.19 | 48.76 ± 0.70 | 27.58 ± 0.61 | 35.39 ± 0.38 | 26.22 ± 0.52 | 28.30 ± 0.29 | **39.70 ± 0.61** |
|
69 |
| radbrt/nb\_nocy\_trf | 56.82 ± 1.63 | 68.20 ± 0.75 | 69.22 ± 1.04 | 31.63 ± 0.29 | 20.32 ± 0.45 | 12.91 ± 0.50 | **38.08 ± 0.75** |
|
70 |
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
## Training procedure
|
73 |
|
|
|
68 |
| Maltehb/-l-ctra-danish-electra-small-uncased-ner-dane | 70.41 ± 1.19 | 48.76 ± 0.70 | 27.58 ± 0.61 | 35.39 ± 0.38 | 26.22 ± 0.52 | 28.30 ± 0.29 | **39.70 ± 0.61** |
|
69 |
| radbrt/nb\_nocy\_trf | 56.82 ± 1.63 | 68.20 ± 0.75 | 69.22 ± 1.04 | 31.63 ± 0.29 | 20.32 ± 0.45 | 12.91 ± 0.50 | **38.08 ± 0.75** |
|
70 |
|
71 |
+
Aside from its high accuracy, it's also substantially **faster** than the previous state-of-the-art:
|
72 |
+
|
73 |
+
| **Model ID** | **Samples/second** | **Model size** |
|
74 |
+
| saattrupdan/nbailab-base-ner-scandi | 4.16 ± 0.18 | 676 GB |
|
75 |
+
| chcaa/da\_dacy\_large\_trf | 0.65 ± 0.01 | 2,090 GB |
|
76 |
+
|
77 |
|
78 |
## Training procedure
|
79 |
|