---
title: corvus-gov-3B
canonical_url: "https://www.modelscope.ai/models/JavaFamily/corvus-gov-3B"
md_url: "https://www.modelscope.ai/models/JavaFamily/corvus-gov-3B.md"
repository: JavaFamily/corvus-gov-3B
last_updated: 2026-10-09
license: "Apache License 2.0"
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama3
architectures:
  - LlamaForCausalLM
base_model:
  - LLM-Research/Llama-3.2-3B-Instruct
base_model_relation: finetune
parameters: 3.2B
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
language:
  - zh
downloads: 6
stars: 0
tags:
  - "政衡"
  - "政企大模型"
  - "政务 AI 大模型"
  - JavaFamily
  - "微调"
  - LLaMA-Factory
  - LoRA
  - SFT
  - "政务领域"
  - "中文对话"
---

# corvus-gov-3B

> corvus-gov-3B - An open-source model by JavaFamily on ModelScope. Corvus-Gov-3B 当大模型从实验室涌向政务大厅，考验的不是才华，而是分寸。行政边界一字之差，政策口径一厘之偏，足以让信任归零。

JavaFamily/corvus-gov-3B is a 3.2B-parameter text-generation model on ModelScope. licensed under Apache License 2.0. derived from LLM-Research/Llama-3.2-3B-Instruct.

- **Repository**: JavaFamily/corvus-gov-3B
- **License**: Apache License 2.0
- **Tasks**: text-generation
- **Parameters**: 3.2B
- **Base model**: LLM-Research/Llama-3.2-3B-Instruct
- **Tags**: 政衡, 政企大模型, 政务 AI 大模型, JavaFamily, 微调, LLaMA-Factory, LoRA, SFT, 政务领域, 中文对话
- **Downloads**: 6
- **Stars**: 0
- **Last updated**: 2026-10-09

Source: https://www.modelscope.ai/models/JavaFamily/corvus-gov-3B

---

# Corvus-Gov-3B
当大模型从实验室涌向政务大厅，考验的不是才华，而是分寸。行政边界一字之差，政策口径一厘之偏，足以让信任归零。

「政衡」corvus-gov 基于 Llama3/Qwen3 基座模型，在百万级中文政务领域对话数据集上完成 SFT 微调。训练采用 LoRA 轻量化微调方案。 以衡为名，百万数据精训为每一句政务回答校准刻度。这不是参数的竞赛，而是关于可信的承诺。政企 AI 落地，自此有衡。

- 训练框架：LLaMA Factory
- 对话模板：`llama3`/`qwen3`

## Training Loss

训练 loss 曲线如下图所示，loss 随训练 step 平稳下降，模型收敛效果良好：

![training loss](https://www.modelscope.cn/models/JavaFamily/corvus-gov-3B/resolve/main/loss_plot.png)

## Training Data

- 数据规模：百万级中文政务领域对话样本
- 训练方式：LoRA SFT 有监督微调
- 训练框架：LLaMA Factory

## Quickstart

### ModelScope Python SDK

```python
from modelscope import AutoTokenizer, AutoModelForCausalLM

model_id = "JavaFamily/corvus-gov-3B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto"
)

messages = [
    {"role": "system", "content": "你是政务领域智能助手，请严谨、准确回答用户问题。"},
    {"role": "user", "content": "请介绍一下政务咨询相关政策。"}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to("cuda")

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.9
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```

### vLLM 快速推理（推荐部署）

```python
from vllm import LLM, SamplingParams

model_id = "JavaFamily/corvus-gov-3B"
sampling_params = SamplingParams(temperature=0.7, top_p=0.9, max_tokens=512)
llm = LLM(model=model_id)

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
outputs = llm.generate(prompt, sampling_params)
print(outputs[0].outputs[0].text)
```

#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

1）ModelScope 下载

```bash
#安装ModelScope
pip install modelscope
```

* CLI 命令下载
```shell
# cli 下载
modelscope download --model JavaFamily/corvus-gov-3B --local_dir ./llama3/corvus‑gov‑3B
```

* SDK下载
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('JavaFamily/corvus-gov-3B')
```

2） Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/JavaFamily/corvus-gov-3B.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>