mlabonne/synthetic_text_to_sql-ShareGPT

---
dataset_info:
features:
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
splits:
- name: train
num_bytes: 78494888
num_examples: 105851
download_size: 31275284
dataset_size: 78494888
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---

# synthetic_text_to_sql

ShareGPT version of [gretelai/synthetic_text_to_sql](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql) using the following code:

```python
from datasets import load_dataset, DatasetDict

# Load the dataset
dataset = load_dataset('gretelai/synthetic_text_to_sql', split='all')

def format_sample(sample):
conversations = [
{
"from": "human",
"value": f"{sample['sql_context']}\n\n{sample['sql_prompt']}"
},
{
"from": "gpt",
"value": f"{sample['sql']}\n\n{sample['sql_explanation']}"
}
]
return {"conversations": conversations}

dataset = dataset.map(format_sample, remove_columns=dataset.column_names)
dataset = DatasetDict({'train': dataset})
```

It means that the `sql_context` and `sql_prompt` fields are concatenated as user instruction, and the `sql` and `sql_explanation` are concatenated as answers.
Ideally, we'd want to steer the model's answer by providing the explanations first.
However, they're not phrased in a way that would make sense if they appeared before the code, which is why I decided to append them after the `sql` field.

Let me know if you think that another formatting would be better.

原始信息汇总

数据集概述

数据集名称

synthetic_text_to_sql

数据集特征

• 名称: conversations
  • 子特征:
    • 名称: from
      • 数据类型: string
    • 名称: value
      • 数据类型: string

数据集划分

• 划分名称: train
  • 示例数量: 105851
  • 数据大小: 78494888字节

下载信息

• 下载大小: 31275284字节
• 数据集大小: 78494888字节

配置

• 配置名称: default
  • 数据文件:
    • 划分: train
      • 路径: data/train-*