byroneverson/shell-cmd-instruct

---
license: apache-2.0
task_categories:
- text-generation
language:
- en
tags:
- instruction-finetuning
pretty_name: Shell Command Instruct
---
# **Used to train models that interact directly with shells**

Follow-up details of my process

- MacOS terminal commands for now. This dataset is still in alpha stages and will be modified.
- Contains 500 somewhat unique training examples so far.
- GPT4 seems like a good candidate for generating more data, licensing would need to be addressed.
- I fine-tuned Solar-10.7B-Instruct-v1.0 with this dataset using a slightly modified version of axolotl. Just a few epochs was enough to get it to output correctly.
- I use oobabooga/text-generation-webui with a custom chat extension for inference. No sandbox is used, it is piped directly into MacOS bash because I'm reckless. C:

- Currently working towards training an MoE (2x7B), multi-modal model (image/text) with this dataset. (BakLLaVA-1-7B + LLaVA-v1.5-7B)

- Inference stages:
1. Send the instruction to the model, expect command.
2. Detect shell command and send to sand-boxed shell.
4. Shell respose should be sent as additional input to model.
5. The final model response should be sent to user from assistant.

TODO:
- Possible "os" column to specify which system the command should be used with, maybe separate datasets for each system type.

## **Sample prompt: (in series, depends on your specific model prompt)**
```
### User:
List files in 'Downloads'

### Command:
ls ~/Downloads
```
```
### Shell:
file1.pdf file2.txt file3.zip

### Assistant:
Listing files in 'Downloads': file1.pdf file2.txt file3.zip
```

原始信息汇总

数据集概述

基本信息

• 许可证: Apache-2.0
• 任务类别: 文本生成
• 语言: 英语
• 标签: 指令微调
• 易读名称: Shell Command Instruct

数据集描述

• 用于训练直接与Shell交互的模型。
• 目前包含500个独特的训练样本。
• 适用于MacOS终端命令。
• 数据集处于Alpha阶段，将持续更新和修改。

使用案例

• 使用此数据集微调了Solar-10.7B-Instruct-v1.0模型。
• 使用oobabooga/text-generation-webui进行推理，直接在MacOS bash中运行。
• 正在开发一个多模态模型（图像/文本），使用此数据集进行训练。

推理流程

1. 向模型发送指令，期望返回命令。
2. 检测Shell命令并发送至沙盒Shell。
3. Shell响应应作为额外输入发送给模型。
4. 最终模型响应应由助手发送给用户。

示例

用户输入

List files in Downloads

命令输出

ls ~/Downloads

Shell输出

file1.pdf file2.txt file3.zip

助手输出

Listing files in Downloads: file1.pdf file2.txt file3.zip