Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,24 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
> There is currently no JaColBERTv2 technical report. For an overall idea, you can refer to the JaColBERTv1 [arXiv Report](https://arxiv.org/abs/2312.16144)
|
4 |
|
|
|
1 |
+
---
|
2 |
+
inference: false
|
3 |
+
datasets:
|
4 |
+
- bclavie/mmarco-japanese-hard-negatives
|
5 |
+
- unicamp-dl/mmarco
|
6 |
+
language:
|
7 |
+
- ja
|
8 |
+
pipeline_tag: sentence-similarity
|
9 |
+
tags:
|
10 |
+
- ColBERT
|
11 |
+
base_model:
|
12 |
+
- cl-tohoku/bert-base-japanese-v3
|
13 |
+
- bclavie/JaColBERT
|
14 |
+
license: mit
|
15 |
+
library_name: RAGatouille
|
16 |
+
---
|
17 |
+
|
18 |
+
|
19 |
+
First version of JaColBERTv2. Weights might be updated in the next few days.
|
20 |
+
|
21 |
+
Current early checkpoint is fully functional and outperforms multilingual-e5-large, BGE-M3 and JaColBERT in early results, but full evaluation TBD.# Intro
|
22 |
|
23 |
> There is currently no JaColBERTv2 technical report. For an overall idea, you can refer to the JaColBERTv1 [arXiv Report](https://arxiv.org/abs/2312.16144)
|
24 |
|