stefan-it/span-marker-base-model-detection

---
license: mit
---

# SpanMarker Base Model Detection

It is relative simply to determine base model of a fine-tuned SpanMarker model:

```python
import os

from huggingface_hub import login, HfApi

hf_token = os.environ.get("HF_TOKEN")
login(token=hf_token, add_to_git_credential=True)
api = HfApi()
```

Please make sure that `HF_TOKEN` is set as environment variable.

After that, list of all SpanMarker models can be retrieved and configuration file is parsed.
Please make sure that `span-marker` library is installed:

```python
from span_marker import SpanMarkerConfig

f_out = open("span_marker_base_model_detection.csv", "wt")

f_out.write("Nr,Model ID,Base Model ID\n")

counter = 1
for span_marker_model in api.list_models(filter="span-marker"):
try:
config = SpanMarkerConfig.from_pretrained(span_marker_model.modelId)

base_model = config.encoder["_name_or_path"]

f_out.write(f"{counter},{span_marker_model.modelId},{base_model}\n")

counter +=1
except Exception as e:
print(e)
f_out.close()
```

原始信息汇总

SpanMarker Base Model Detection

数据集描述

该数据集用于检测经过微调的SpanMarker模型的基础模型。

数据集使用步骤

1. 环境设置：

   • 确保环境变量HF_TOKEN已设置。

2. 代码示例：

   • 导入必要的库并登录Hugging Face Hub。
   • 列出所有SpanMarker模型并解析配置文件。
   • 确保已安装span-marker库。

3. 数据输出：

   • 将检测结果写入CSV文件span_marker_base_model_detection.csv，包含模型编号、模型ID和基础模型ID。