---
library_name: transformers
license: apache-2.0
datasets:
- nohurry/Opus-4.6-Reasoning-3000x-filtered
language:
- ab
base_model:
- Qwen/Qwen3.5-35B-A3B
new_version: Qwen/Qwen3.5-35B-A3B
pipeline_tag: text-classification
tags:
- code
---
license: apache-2.0
tags:
- text-classification
- glue
- mrpc
datasets:
- glue
language:
- en
---

# bert-finetuned-mrpc-v2

Fine-tuned BERT-base-uncased on MRPC (GLUE benchmark) for paraphrase detection.

## Model details

- Base model: google-bert/bert-base-uncased
- Task: Binary classification (paraphrase or not)
- Language: English
- Training data: GLUE MRPC train split
- Evaluation data: GLUE MRPC validation split
- Epochs: 3
- Batch size: 16
- Learning rate: 2e-5

## How to use

```python
from transformers import pipeline

classifier = pipeline("text-classification", model="tu-usuario/bert-finetuned-mrpc-v2")
result = classifier("The two sentences mean the same thing.")
print(result)