GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
DS4AI-UPB
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
DS4AI-UPB
Model Tree
Qwen/Qwen2.5-32B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Language | Exact match | Relation match | Entity match |
|---|---|---|---|
| English | 0.704 | 0.802 | 0.786 |
| Romanian | 0.641 | 0.788 | 0.722 |
QLoRA raises exact match by about 40pp over zero-shot in both languages. On this task a lightweight two-encoder pipeline (a span detector plus the relation classifier) matches or exceeds the fine-tuned LLMs at a fraction of the cost — see the paper.
Qwen/Qwen2.5-32B-Instruct, loaded in 4-bitpython
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct", load_in_4bit=True, device_map="auto")model = PeftModel.from_pretrained(base, "DS4AI-UPB/qwen25-ro-e2e-lora")tok = AutoTokenizer.from_pretrained("DS4AI-UPB/qwen25-ro-e2e-lora")
The prompt format and expected JSON output schema are in the run_inference.py script in the code repository.
The Romanian training data is machine-translated with automatic post-validation, not a human gold standard. Entity-level translation artifacts affect end-to-end evaluation in particular; see the paper for the analysis.
bibtex
@misc{vasile2026crosslingual,title = {Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian},author = {Vasile, Drago\c{s}-Mitru\c{t} and Apostol, Elena-Simona and Toma, \c{S}tefan-Adrian and Paschke, Adrian and Truic\u{a}, Ciprian-Octavian},year = {2026},note = {Preprint}}