Downloads · 30 days
7
13% of all-time downloads
distilbert-lora-sst2
Sara-1990/distilbert-lora-sst2
distilbert-lora-sst2 is a text classification model from Sara-1990. Use it when you need a label for a piece of text. It is set up for peft. The card lists the license as mit.
Fine-tuned distilbert-base-uncased for binary sentiment classification using parameter-efficient LoRA (r=8) via the PEFT library.
All-time downloads
52
Public
Repo size
3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3 MB · 81%
At a glance
- Task
- Text Classification
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jun 23, 2026
- Updated
- Aug 13, 2026
- SHA
- 1270f3d4
Try a prompt
Datasets
Model card
From the Hugging Face model README
DistilBERT fine-tuned on SST-2 with LoRA
Fine-tuned distilbert-base-uncased for binary sentiment classification
using parameter-efficient LoRA (r=8) via the PEFT library.
Accuracy: ~92% on SST-2 validation set
Trainable parameters: ~0.8% of total
Usage
from transformers import pipeline classifier = pipeline("text-classification", model="Sara-1990/distilbert-lora-sst2") classifier("The paper results are surprisingly strong.")
Training details
- Base model: distilbert-base-uncased
- LoRA rank: 8, alpha: 16
- Epochs: 3, batch size: 16
- Hardware: [Apple MacBook Air CPU]
Links
- Task
- Text Classification
- Library
- peft
- License
- mit
- Languages
- en
- Created
- Jun 23, 2026
- Updated
- Aug 13, 2026