Downloads · 30 days
7
8% of all-time downloads
imdb-roberta-lora-v2
Denizhaan/imdb-roberta-lora-v2
imdb-roberta-lora-v2 is a text classification model from Denizhaan. Use it when you need a label for a piece of text. It is set up for peft.
LoRA-adapted roberta-base for binary sentiment classification on the IMDB Large Movie Review Dataset. One of four base models in a parameter-efficient stacking ensemble described in "Parameter-Efficient Fine-Tuning En…
All-time downloads
83
Public
Repo size
4.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.7 MB · 57%
At a glance
- Task
- Text Classification
- Library
- peft
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Aug 22, 2026
- SHA
- 05e16d46
Try a prompt
Base models
Model card
From the Hugging Face model README
RoBERTa-base + LoRA — IMDB Sentiment Classification
LoRA-adapted roberta-base for binary sentiment classification on the IMDB Large Movie Review Dataset. One of four base models in a parameter-efficient stacking ensemble described in "Parameter-Efficient Fine-Tuning Ensembles for Sentiment Analysis" (IDAP 2026).
Results (25,000-example IMDB test set)
| Metric | Value |
|---|---|
| Accuracy | 95.60% |
| F1 | 95.62% |
| Precision | 95.23% |
| Recall | 96.01% |
| ROC-AUC | 99.00% |
LoRA Configuration
| Hyperparameter | Value |
|---|---|
| Rank (r) | 16 |
| Alpha | 32 |
| Dropout | 0.1 |
| Target modules | query, value |
| Trainable parameters | 1,181,954 (0.94% of 125.8M total) |
| Precision | fp16 |
Loading
from transformers import RobertaTokenizer, RobertaForSequenceClassification
from peft import PeftModel
tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
base = RobertaForSequenceClassification.from_pretrained("roberta-base", num_labels=2)
model = PeftModel.from_pretrained(base, "Denizhaan/imdb-roberta-lora-v2")
model.eval()
Citation
If you use this model, please cite our paper (details in the GitHub repository).
Framework versions
- PEFT 0.19.1
- Task
- Text Classification
- Library
- peft
- Created
- Jun 6, 2026
- Updated
- Aug 22, 2026