Downloads · 30 days
0
Yakk99/scihigh2026-subtask1-qwen72b-qlora
scihigh2026-subtask1-qwen72b-qlora is a summarization model from Yakk99. Use it when you need a shorter version of a longer text. The card lists the license as apache-2.0.
QLoRA adapter (4-bit NF4 base, LoRA r=16 on attention+MLP).
Downloads · 30 days
0
Access
Public
Updated Aug 12, 2026
Repo size
433 MB
Likes
0
Public
Click a slice to open those files.
.safetensors421 MB · 97%
From the Hugging Face model README
QLoRA adapter (4-bit NF4 base, LoRA r=16 on attention+MLP).
Fine-tuned for the FIRE 2026 SciHigh shared task, Subtask 1: generating research highlights from scientific paper abstracts (MixSub corpus).
<paper title> | <abstract> (corpus punctuation-stripped
style; abstracts repaired via DOI-verified Semantic Scholar recovery)| file | purpose |
|---|---|
train_final.py | standalone training recipe that produced this model |
train_final.ipynb | notebook version of the same recipe |
infer_test.py | test-set submission CSV generation |
final/ | full data pipeline: abstract recovery, title fetch, dataset build, submission validation |