HiTZ
/

Token Classification
Transformers
Safetensors
deberta-v2
question-answering
Inference Endpoints
ragerri commited on
Commit
7973d3d
1 Parent(s): 19202d9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -39,6 +39,10 @@ which includes English, French, Italian and Spanish.
39
 
40
  The model scores **74.64 F1 partial match** (as defined in [SQuAD extractive QA task](https://huggingface.co/datasets/rajpurkar/squad_v2)) averaged across the 4 languages.
41
 
 
 
 
 
42
  <!--<img src="https://raw.githubusercontent.com/hitz-zentroa/multilingual-abstrct/main/resources/multilingual-abstrct-results.png" style="width: 75%;"> -->
43
 
44
  ### Fine-tuning hyperparameters
 
39
 
40
  The model scores **74.64 F1 partial match** (as defined in [SQuAD extractive QA task](https://huggingface.co/datasets/rajpurkar/squad_v2)) averaged across the 4 languages.
41
 
42
+ - **tags:** to delimit explanations of the correct answers and the rest at token level.
43
+ - 0: explanation of the correct answer
44
+ - 1: others
45
+
46
  <!--<img src="https://raw.githubusercontent.com/hitz-zentroa/multilingual-abstrct/main/resources/multilingual-abstrct-results.png" style="width: 75%;"> -->
47
 
48
  ### Fine-tuning hyperparameters