---
title: bert-base-cased-STS-B
canonical_url: "https://www.modelscope.cn/models/textattack/bert-base-cased-STS-B"
md_url: "https://www.modelscope.cn/models/textattack/bert-base-cased-STS-B.md"
repository: textattack/bert-base-cased-STS-B
last_updated: 2025-09-29
pipeline_tag: text-classification
tasks:
  - text-classification
model_type:
  - bert
architectures:
  - BertForSequenceClassification
library_name:
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 85
stars: 0
---

# bert-base-cased-STS-B

> bert-base-cased-STS-B - textattack 在 ModelScope 开源的模型。TextAttack Model Card This bert-base-cased model was fine-tuned for sequence classificationusing TextAttack and the glue dataset loaded using the nlp library. The model was fine-tuned for 3 epochs with a…

textattack/bert-base-cased-STS-B 是 ModelScope 魔搭社区上的text-classification模型，可用 deploy_task emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: textattack/bert-base-cased-STS-B
- **Tasks**: text-classification
- **Inference backends**: deploy_task emb, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 85
- **Stars**: 0
- **Last updated**: 2025-09-29

Source: https://www.modelscope.cn/models/textattack/bert-base-cased-STS-B

---

## TextAttack Model Card    
    This `bert-base-cased` model was fine-tuned for sequence classificationusing TextAttack 
    and the glue dataset loaded using the `nlp` library. The model was fine-tuned 
    for 3 epochs with a batch size of 128, a learning 
    rate of 1e-05, and a maximum sequence length of 128. 
    Since this was a regression task, the model was trained with a mean squared error loss function. 
    The best score the model achieved on this task was 0.8244429996636282, as measured by the 
    eval set pearson correlation, found after 2 epochs.
    
    For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).