Hugging Face's logo

sultan
/
ArabicT5-49GB-small

Text2Text Generation
Transformers
PyTorch
JAX
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
sultan commited on
Commit
beef5d4
·
1 Parent(s): bfc0253

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -43,11 +43,24 @@ Total Corpora size is 49GB. This model uses an efficient implementation of T5 wh
43
  | Generative | ArabicT5-49GB-small | <center>72.4/85.1 |<center>96.4|<center>70.2/73.4|<center>61.0|<center>30.2|
44
  | Generative | ArabicT5-17GB-base | <center>73.3/86.1 |<center>96.4|<center>70.4/73.0|<center>59.8|<center>30.3|
45
  | Generative | ArabicT5-49GB-base | <center>72.1/85.1 |<center>96.5|<center>71.3/74.1|<center>60.4|<center>30.9|
 
 
 
 
 
 
 
 
 
 
 
 
46
  | Generative | ArabicT5-17GB-large | <center>75.5/87.1 |<center>96.5| <center>72.2/75.2|<center>61.7|<center>31.7|
47
  | Exctractive | AraBERTv02-Large | <center>73.7/86.0 |<center>96.4|<center>69.5/71.8|<center>-|<center> N/A|
48
  | Exctractive | AraBERTv2-Large | <center>64.5/82.2 |<center>96.5|<center>70.0/72.4|<center>-|<center> N/A|
49
  | Exctractive | AraELECTRA-base | <center>74.9/86.7 |<center>96.4|<center>69.6/72.3|<center>-|<center>N/A|
50
- | Exctractive | ArabicTransformer-base | <center>75.4/87.2 |<center>96.6|<center>70.8/74.0|<center>-|<center> N/A|
 
51
 
52
  Evaluation Metrics: TyDi QA (EM/F1), HARD (Accuracy), Sentiment Analysis (Accuracy / F1-PN positive-negative), Sarcasm Detection (F1-sarcastic), XL-SUM (Rouge-L with Stemmer).
53
 
 
43
  | Generative | ArabicT5-49GB-small | <center>72.4/85.1 |<center>96.4|<center>70.2/73.4|<center>61.0|<center>30.2|
44
  | Generative | ArabicT5-17GB-base | <center>73.3/86.1 |<center>96.4|<center>70.4/73.0|<center>59.8|<center>30.3|
45
  | Generative | ArabicT5-49GB-base | <center>72.1/85.1 |<center>96.5|<center>71.3/74.1|<center>60.4|<center>30.9|
46
+ | Generative | ArabicT5-17GB-large | <center>**75.5/87.1** |<center>**96.5**| <center>**72.2/75.2**|<center>**61.7**|<center>**31.7**|
47
+
48
+
49
+
50
+ ## ArabicT5 vs Extractive Arabic BERT-like Models
51
+
52
+ | Model Type | Model | <center>TyDi QA| <center>HARD| <center>ArSarcasm-v2-Sentiment| <center>ArSarcasm-v2-Sarcasm| XL-SUM |
53
+ |--------------|------------------------|---------------------|----------------|-----------------|------------|------------|
54
+ | Generative | ArabicT5-17GB-small | <center>70.8/84.8 |<center>96.4|<center>68.9/71.2|<center>58.9|<center>29.2|
55
+ | Generative | ArabicT5-49GB-small | <center>72.4/85.1 |<center>96.4|<center>70.2/73.4|<center>61.0|<center>30.2|
56
+ | Generative | ArabicT5-17GB-base | <center>73.3/86.1 |<center>96.4|<center>70.4/73.0|<center>59.8|<center>30.3|
57
+ | Generative | ArabicT5-49GB-base | <center>72.1/85.1 |<center>96.5|<center>71.3/74.1|<center>60.4|<center>30.9|
58
  | Generative | ArabicT5-17GB-large | <center>75.5/87.1 |<center>96.5| <center>72.2/75.2|<center>61.7|<center>31.7|
59
  | Exctractive | AraBERTv02-Large | <center>73.7/86.0 |<center>96.4|<center>69.5/71.8|<center>-|<center> N/A|
60
  | Exctractive | AraBERTv2-Large | <center>64.5/82.2 |<center>96.5|<center>70.0/72.4|<center>-|<center> N/A|
61
  | Exctractive | AraELECTRA-base | <center>74.9/86.7 |<center>96.4|<center>69.6/72.3|<center>-|<center>N/A|
62
+ | Exctractive | ArabicTransformer-base | <center>**75.4/87.2** |<center>**96.6**|<center>70.8/74.0|<center>-|<center> N/A|
63
+
64
 
65
  Evaluation Metrics: TyDi QA (EM/F1), HARD (Accuracy), Sentiment Analysis (Accuracy / F1-PN positive-negative), Sarcasm Detection (F1-sarcastic), XL-SUM (Rouge-L with Stemmer).
66