Upload doda_independent_results.csv with huggingface_hub
Browse files- doda_independent_results.csv +13 -0
doda_independent_results.csv
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
name,source,algorithm,architecture,vocab_size,n_texts,fertility,cpt,exact_match
|
| 2 |
+
concat_bpe_8000,ours,bpe,concatenated,8000,10000,2.2493365838654813,2.687371473272056,0.9997
|
| 3 |
+
concat_wordpiece_16000,ours,wordpiece,concatenated,16000,10000,2.0290824072414515,2.9837349169014926,0.9997
|
| 4 |
+
concat_bpe_32000,ours,bpe,concatenated,32000,10000,1.9088338778378482,3.1857039546146164,0.9997
|
| 5 |
+
CaMeLBERT-MSA,external_msa,WordPiece,shared,30000,10000,3.666749920577788,1.5885688345700721,0.9848
|
| 6 |
+
Asafaya-BERT,external_msa,WordPiece,shared,32000,10000,3.1872837153369504,1.8326136998271592,0.946
|
| 7 |
+
Aranizer-SP-86k,external_msa,SentencePiece,shared,86000,10000,3.0218238644117323,1.932848411795582,0.9871
|
| 8 |
+
B2BERT,external_msa,WordPiece,shared,30000,10000,3.666749920577788,1.5885688345700721,0.9848
|
| 9 |
+
DarijaBERT-ar,external_darija,WordPiece,shared,80000,10000,2.7214379379770555,2.17268830784525,0.9445
|
| 10 |
+
DarijaBERT-az,external_darija,WordPiece,shared,110000,10000,1.3138639463640935,4.552913171884771,0.9445
|
| 11 |
+
Moroccan-Darija-Tokenizer,external_darija,BPE,shared,30000,10000,3.328279298136504,1.7596048679100837,0.0003
|
| 12 |
+
Translit-Darija,external_darija,BPE,shared,30000,10000,1.869362422920217,3.206997841360009,0.0302
|
| 13 |
+
Qwen2.5-Darija,external_darija,SentencePiece,shared,151643,10000,2.6158528813017052,2.255188783435299,1.0
|