HeyDunaX commited on
Commit
d551d1f
·
verified ·
1 Parent(s): 755cc06

add model card

Browse files
Files changed (1) hide show
  1. README.md +34 -0
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - vi
4
+ - ede
5
+ tags:
6
+ - cross-lingual-retrieval
7
+ - sentencepiece-tokenizer
8
+ - colbert
9
+ - EViRAL
10
+ ---
11
+
12
+ # ColBERT + SentencePiece — EViRAL
13
+
14
+ Task: Ede query → Vietnamese passage retrieval
15
+
16
+ ## Eval Results
17
+
18
+ | Metric | Validation | Test |
19
+ |---------|-----------|--------|
20
+ | nDCG@1 | 0.0004 | 0.0004 |
21
+ | nDCG@5 | 0.0009 | 0.0011 |
22
+ | nDCG@10 | 0.0018 | 0.0019 |
23
+ | MRR@10 | 0.0019 | 0.0020 |
24
+ | R@50 | 0.0204 | 0.0206 |
25
+ | R@100 | 0.0370 | 0.0389 |
26
+
27
+ ## Checkpoints
28
+ | file | description |
29
+ |---|---|
30
+ | mlm.pt | MLM pre-trained encoder |
31
+ | align.pt | cross-lingual aligned encoder |
32
+ | finetune.pt | contrastive fine-tuned encoder (best val) |
33
+ | sp_tokenizer/spm.model | SentencePiece model |
34
+ | sp_tokenizer/spm.vocab | SentencePiece vocab |