---
title: ShiZhi
canonical_url: "https://www.modelscope.cn/models/ZhitianHou/ShiZhi"
md_url: "https://www.modelscope.cn/models/ZhitianHou/ShiZhi.md"
repository: ZhitianHou/ShiZhi
chinese_name: ShiZhi
last_updated: 2026-01-20
license: "Apache License 2.0"
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - Qwen2-0.5B-Instruct
base_model_relation: adapter
parameters: 4.4M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 57
stars: 0
---

# ShiZhi

> ShiZhi - ZhitianHou 在 ModelScope 开源的模型。Model Card for LegalReasoningModel

ZhitianHou/ShiZhi 是 ModelScope 魔搭社区上的 4.4M 参数text-generation模型，采用 Apache License 2.0 许可，基于 Qwen2-0.5B-Instruct 构建。

- **Repository**: ZhitianHou/ShiZhi
- **License**: Apache License 2.0
- **Tasks**: text-generation
- **Parameters**: 4.4M
- **Base model**: Qwen2-0.5B-Instruct
- **Downloads**: 57
- **Stars**: 0
- **Last updated**: 2026-01-20

Source: https://www.modelscope.cn/models/ZhitianHou/ShiZhi

---

# Model Card for LegalReasoningModel

[中文](README_zh.md)



A 0.5B LLM fine-tuned for generating the "Court's Reasoning" section in Chinese judicial documents.



## Model Details

### Model Description

This model is fine-tuned based on **Qwen2-0.5B-Instruct**, using a dataset of Chinese judicial documents from 2019 to 2021 that has been rigorously cleaned. Due to the need to handle privacy issues in judicial documents, the full dataset will be released in the future.



- **Language(s) (NLP):** Chinese/zh
- **License:** Apache License 2.0
- **Finetuned from model:** Qwen2-0.5B-Instruct



## How to Get Started with the Model

```python
from swift.llm import (
    get_model_tokenizer, get_template, inference, ModelType, get_default_template_type,
)
from tqdm import tqdm
from swift.tuners import Swift

data = [{"fact": "经审理查明，..."}, {"fact": "经审理查明，..."}]

ckpt_dir = "ZhitianHou/LegalReasoningModel"
model_type = ModelType.qwen2_0_5b_instruct
template_type = get_default_template_type(model_type)

model, tokenizer = get_model_tokenizer(model_type, model_kwargs={'device_map': 'auto'},
                                       model_id_or_path="")

model = Swift.from_pretrained(model, ckpt_dir, inference_mode=True)

model.generation_config.max_new_tokens = 512

template = get_template(template_type, tokenizer)

for sample in tqdm(data):
    fact = sample["fact"]
    response, history = inference(model, template, f"事实描述:\n{fact}\n法院推理:\n")
    print(response)
```



## Training Details

### Training Data

The training data is a dataset of Chinese judicial documents from 2019 to 2021 that has been rigorously cleaned, [ChineseLR](https://www.modelscope.cn/datasets/freshman8888/ChineseLR). Due to the need to handle privacy issues in judicial documents, the full dataset will be released in the future.



### Framework versions

- PEFT 0.12.0



## Model Disclaimer

1. **Usage Restriction**: This model is developed and provided **exclusively for academic research purposes** , aiming to offer tool support for academic exploration, technical verification, and theoretical research in relevant fields. The use of this model for any commercial purposes (including but not limited to product development, commercial services, profit - making activities, etc.), illegal activities, or scenarios that violate laws, regulations, public order, and good customs is strictly prohibited.
2. **Statement on Result Validity**: All content generated by this model (including texts, data, conclusions, etc.) has not undergone systematic manual verification and accuracy review. It may contain issues such as factual deviations, logical omissions, outdated information, or ambiguous expressions. The model cannot make any guarantees regarding the authenticity, completeness, reliability, or applicability of the generated content.
3. **Explanation on Preference Adaptation**: The training data and optimization objectives of this model are not specifically designed to "conform to universal human preferences" or "meet the subjective needs of specific groups". The generated content may differ from the values, aesthetic preferences, and cognitive habits of different users. The model does not guarantee that the generated results will meet the subjective expectations of any individual or group.
4. **Liability Definition**: For any subsequent actions (including academic citation, decision - making reference, content dissemination, etc.) based on the content generated by this model, the risks and responsibilities shall be borne solely by the person who carries out the actions. The model developer shall not be liable for any direct or indirect losses (including but not limited to academic errors, decision - making deviations, reputation damage, etc.) caused by the use of the content of this model.
5. **Usage Recommendation**: It is recommended that users, when using the content generated by this model, conduct cross - verification with their own professional knowledge and reliable information sources, make independent judgments on the rationality and accuracy of the content, and avoid directly using the model output as the sole basis.