Downloads · 30 days
20
39% of all-time downloads
RKMVNLP-scihigh-task1-bart-large-run1
namra07/RKMVNLP-scihigh-task1-bart-large-run1
RKMVNLP-scihigh-task1-bart-large-run1 is a summarization model from namra07. Use it when you need a shorter version of a longer text. The card lists the license as mit.
BART-Large fine-tuned with LoRA for research highlight generation (FIRE SciHigh Subtask 1, MixSub-SciHigh). Team RKMVNLP.
All-time downloads
51
Public
Parameters
406M
813 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors813 MB · 100%
At a glance
- Task
- Summarization
- License
- mit
- Model type
- bart
- Access
- Public
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026
- SHA
- 208bdf2f
Try a prompt
Base models
Model card
From the Hugging Face model README
RKMVNLP-scihigh-task1-bart-large-run1
BART-Large fine-tuned with LoRA for research highlight generation (FIRE SciHigh Subtask 1, MixSub-SciHigh). Team RKMV_NLP.
- Base model:
facebook/bart-large - Adapter: LoRA (r=16, alpha=32) on q/k/v/out_proj + fc1/fc2, merged into the base.
- Decoding: num_beams=6, length_penalty=0.8, no_repeat_ngram_size=3, min_length=45.
- Validation ROUGE-L F1 (decoding sweep best): ~0.248.
Input = paper abstract, output = research highlights.
- Task
- Summarization
- Type
- bart
- License
- mit
- Languages
- en
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026