Update README.md

README.md

@@ -14,7 +14,7 @@ tags:
 
 # Intro
 
-> [Technical Report]() (direct PDF, arXiv coming)
+> [Technical Report](https://ben.clavie.eu/JColBERT_v1.pdf) (direct PDF, arXiv coming)
 
 Welcome to JaColBERT version 1, the initial release of JaColBERT, a Japanese-only document retrieval model based on [ColBERT](https://github.com/stanford-futuredata/ColBERT).
 
@@ -22,7 +22,7 @@ It outperforms previous common Japanese models used for document retrieval, and
 
 JaColBERT is only an initial release: it is trained on only 10 million triplets from a single dataset. This is a first version, hopefully demonstrating the strong potential of this approach.
 
-The information on this model card is minimal and intends to give an overview. I've been asked before to make a citeable version, **please refer to the [Techical Report](placeholder)** for more information.
+The information on this model card is minimal and intends to give an overview. I've been asked before to make a citeable version, **please refer to the [Techical Report](https://ben.clavie.eu/JColBERT_v1.pdf)** for more information.
 
 # Why use a ColBERT-like approach for your RAG application?