---
title: llama3-8b-agent-instruct-v2-GGUF
canonical_url: "https://www.modelscope.ai/models/swift/llama3-8b-agent-instruct-v2-GGUF"
md_url: "https://www.modelscope.ai/models/swift/llama3-8b-agent-instruct-v2-GGUF.md"
repository: swift/llama3-8b-agent-instruct-v2-GGUF
last_updated: 2025-09-06
license: "Apache License 2.0"
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - gguf
  - pytorch
frameworks:
  - Pytorch
downloads: 205
stars: 0
tags:
  - gguf
---

# llama3-8b-agent-instruct-v2-GGUF

> llama3-8b-agent-instruct-v2-GGUF - An open-source model by swift on ModelScope. Fine-tuning the llama3-8b-instruct model using the msagent-pro dataset and the lossscale technique with swift, GGUF版本。模型使用llama.cpp转换，包括FP16，Q80，Q5KM, Q6KM, Q4KM等多个精度。

swift/llama3-8b-agent-instruct-v2-GGUF is a text-generation model on ModelScope. licensed under Apache License 2.0.

- **Repository**: swift/llama3-8b-agent-instruct-v2-GGUF
- **License**: Apache License 2.0
- **Tasks**: text-generation
- **Tags**: gguf
- **Downloads**: 205
- **Stars**: 0
- **Last updated**: 2025-09-06

Source: https://www.modelscope.ai/models/swift/llama3-8b-agent-instruct-v2-GGUF

---

Fine-tuning the llama3-8b-instruct model using the [msagent-pro](https://modelscope.cn/datasets/iic/MSAgent-Pro/) dataset and the loss_scale technique with swift, GGUF版本。模型使用llama.cpp转换，包括FP16，Q8_0，Q5_K_M, Q6_K_M, Q4_K_M等多个精度。


您可以通过ModelScope命令行来下载指定精度的GGUF文件到本地文件夹
```bash
#安装ModelScope
pip install modelscope
```

例如下载Q5_K_M可通过如下命令：
```bash
modelscope download --model swift/llama3-8b-agent-instruct-v2-GGUF llama3-8b-agent-instruct-v2-Q5_K_M.gguf  --local_dir ./
```

您也可以下载整个repo：

SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('swift/llama3-8b-agent-instruct-v2-GGUF')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/swift/llama3-8b-agent-instruct-v2-GGUF.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>