Hugging Face's logo

DS4AI-UPB
/
gemma4-ro-e2e-lora

Text Generation
PEFT
Safetensors
Romanian
English
relation-extraction
romanian
cross-lingual
qlora
lora
end-to-end
conversational
Model card Files
xet
 Community
cipriantruica commited on
Commit
01eca9c
·
verified ·
1 Parent(s): 51e2e74

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -18,6 +18,14 @@ pipeline_tag: text-generation
18
 
19
  # Gemma 4 31B QLoRA adapter — Romanian/English End-to-End Relation Extraction
20
 
 
 
 
 
 
 
 
 
21
  QLoRA adapter for `google/gemma-4-31b-it`, fine-tuned for **End-to-End Relation Extraction** on a Romanian translation of SemEval-2010 Task 8 plus the original English data. Unlike the classification adapter, entity tags are not given: the model reads a plain sentence and generates both entities and the relation between them as a single structured output.
22
 
23
  <!-- This adapter accompanies the SYNASC 2026 paper *"Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian"*. -->
 
18
 
19
  # Gemma 4 31B QLoRA adapter — Romanian/English End-to-End Relation Extraction
20
 
21
+ [Dragoș Mitruț Vasile](https://scholar.google.com/citations?user=eD-SutAAAAAJ) · [Elena-Simona Apostol](https://scholar.google.com/citations?user=XUZcjpEAAAAJ) · [Stefan-Adrian Toma](https://scholar.google.com/citations?user=wsz8cUgAAAAJ) · [Adrian Paschke](https://scholar.google.com/citations?user=D_ZARycAAAAJ) · [Ciprian-Octavian Truică](https://scholar.google.com/citations?user=ZOKqr-QAAAAJ)
22
+
23
+ [![Paper](https://img.shields.io/badge/Paper-InProgress-blue)](https://When-Paper-Appears-it-Will-Work.com)
24
+ [![arXiv](https://img.shields.io/badge/arXiv-WIP-b31b1b)](https://arxiv.org/abs/WIP)
25
+ [![Website](https://img.shields.io/badge/Project-Website-green)](https://github.com/DS4AI-UPB/crosslingual-romanian-re)
26
+ [![GitHub](https://img.shields.io/badge/GitHub-Code-black?logo=github)](https://github.com/DS4AI-UPB/crosslingual-romanian-re)
27
+ [![License](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey)](https://creativecommons.org/licenses/by-nc-sa/4.0/)
28
+
29
  QLoRA adapter for `google/gemma-4-31b-it`, fine-tuned for **End-to-End Relation Extraction** on a Romanian translation of SemEval-2010 Task 8 plus the original English data. Unlike the classification adapter, entity tags are not given: the model reads a plain sentence and generates both entities and the relation between them as a single structured output.
30
 
31
  <!-- This adapter accompanies the SYNASC 2026 paper *"Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian"*. -->