distilbert-imdb-lora

Model Card for Model ID

Model Details

Model Description

Fine-tuned version of distilbert-base-uncased for binary sentiment classification, adapted using LoRA (Low-Rank Adaptation) rather than full fine-tuning.

• Developed by: Mohammad (moh0405)
• Model type: Text classification (sequence classification)
• Language(s): English
• License: Apache 2.0
• Finetuned from model: distilbert-base-uncased

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

Classifies English-language text (originally movie reviews) as POSITIVE or NEGATIVE sentiment. Suitable for quick sentiment tagging tasks similar in style to IMDB reviews.

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

Not intended for nuanced/mixed sentiment detection, non-English text, or domains far from movie reviews (e.g. financial sentiment, medical text) without further fine-tuning. Trained on a small subset for a learning exercise — not validated for production use.

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

​```python from transformers import pipeline

classifier = pipeline("text-classification", model="moh0405/distilbert-imdb-lora") result = classifier("This movie was surprisingly good.") print(result) ​```

[More Information Needed]

Training Details

Training Data

Subset of the IMDB movie review dataset (stanfordnlp/imdb) — 2,000 training examples, 500 evaluation examples, randomly sampled (seed=42) from the full 25,000/25,000 split. [More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Method: LoRA (PEFT), r=8, alpha=16, dropout=0.1, target_modules=["q_lin","v_lin"]
• Trainable parameters: 739,586 / 67,694,596 total (1.09%)
• Epochs: 1
• Batch size: 16 (train), 32 (eval)
• Training regime: fp32

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

500-example held-out split from stanfordnlp/imdb test set.

Metrics

Accuracy

Factors

[More Information Needed]

[More Information Needed]

Results

Stage	Accuracy
Before fine-tuning	50.8%
After fine-tuning (1 epoch)	78.6%

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

Apple Mac Mini (Apple Silicon, MPS backend)

Software

transformers, peft, datasets, PyTorch

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]