README.md

---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2.5-7B
tags:
- capability-tagging
- task
- qwen
---
# Model Card for CDT-Task-Tagger
This model is a component of the **Cognition-Domain-Task (CDT) framework**, a comprehensive capability framework for Large Language Models presented in our paper CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task. It has been specifically fine-tuned to classify a given instruction into one of 16 task types.

## Model Details

### Model Description
This model identifies the fundamental task a user wants the LLM to perform.

- **Model type:** Qwen2ForCausalLM
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model:** Qwen2.5-7B-Base

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/Alessa-mo/CDT
- **Paper Link:** https://arxiv.org/abs/2509.24422

### Basic Usage
Please refer to https://github.com/Alessa-mo/CDT. You can run the following scripts to tag the cognition labels.
```bash
cd tag_annotate
export CUDA_VISIBLE_DEVICES=0
python annotate.py \
    --data_path path/to/your/data \
    --output_dir path/to/output/dir \
    --model_path CDT-Task-Tagger \
    --prompt_file ./prompt/annotation_prompt.jsonl \
    --cognition_skill_file ./prompt/cognition.json \
    --domain_skill_file ./prompt/domain.json \
    --task_skill_file ./prompt/task.json \
    --tag_type "task" \
    --batch_size 32
```
**Note**: Make sure your data is a JSON file and has the following format:
```json
[
    {
        "messages": [
            {
                "role": "user",
                "content": "xxxx"
            },
            {
                "role": "assistant",
                "content": "xxxx"
            }
        ]
    },
]
```
## Citation
If you find this model useful, please cite:
```bash
@misc{mo2025cdtcomprehensivecapabilityframework,
      title={CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task}, 
      author={Haosi Mo and Xinyu Ma and Xuebo Liu and Derek F. Wong and Yu Li and Jie Liu and Min Zhang},
      year={2025},
      eprint={2509.24422},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2509.24422}, 
}
```