mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-09-11 23:52:50 +08:00
Merge pull request #3490 from khazic/main
Added the second sharegpt format Former-commit-id: 282b5d5b1f38012fb1b1875ede510312bf2bcab4
This commit is contained in:
hoshi-hiyouga
GitHub
commit
b9bee7ae27
113
data/README.md
113
data/README.md
@ -1,4 +1,4 @@
|
||||
If you are using a custom dataset, please provide your dataset definition in the following format in `dataset_info.json`.
|
||||
If you are using a custom dataset, please add your **dataset description** to `dataset_info.json` according to the following format. We also provide several examples in the next section.
|
||||
|
||||
```json
|
||||
"dataset_name": {
|
||||
@ -33,7 +33,7 @@ If you are using a custom dataset, please provide your dataset definition in the
|
||||
}
|
||||
```
|
||||
|
||||
Given above, you can use the custom dataset via specifying `--dataset dataset_name`.
|
||||
After that, you can load the custom dataset by specifying `--dataset dataset_name`.
|
||||
|
||||
----
|
||||
|
||||
@ -54,10 +54,11 @@ Currently we support dataset in **alpaca** or **sharegpt** format, the dataset i
|
||||
]
|
||||
```
|
||||
|
||||
Regarding the above dataset, the `columns` in `dataset_info.json` should be:
|
||||
Regarding the above dataset, the description in `dataset_info.json` should be:
|
||||
|
||||
```json
|
||||
"dataset_name": {
|
||||
"file_name": "data.json",
|
||||
"columns": {
|
||||
"prompt": "instruction",
|
||||
"query": "input",
|
||||
@ -70,28 +71,60 @@ Regarding the above dataset, the `columns` in `dataset_info.json` should be:
|
||||
|
||||
The `query` column will be concatenated with the `prompt` column and used as the user prompt, then the user prompt would be `prompt\nquery`. The `response` column represents the model response.
|
||||
|
||||
The `system` column will be used as the system prompt. The `history` column is a list consisting string tuples representing prompt-response pairs in the history. Note that the responses in the history **will also be used for training**.
|
||||
The `system` column will be used as the system prompt. The `history` column is a list consisting string tuples representing prompt-response pairs in the history. Note that the responses in the history **will also be used for training** in supervised fine-tuning.
|
||||
|
||||
For the pre-training datasets, only the `prompt` column will be used for training.
|
||||
|
||||
For the preference datasets, the `response` column should be a string list whose length is 2, with the preferred answers appearing first, for example:
|
||||
For the **pre-training datasets**, only the `prompt` column will be used for training, for example:
|
||||
|
||||
```json
|
||||
{
|
||||
"instruction": "user instruction",
|
||||
"input": "user input",
|
||||
"output": [
|
||||
"chosen answer",
|
||||
"rejected answer"
|
||||
]
|
||||
[
|
||||
{"text": "document"},
|
||||
{"text": "document"}
|
||||
]
|
||||
```
|
||||
|
||||
Regarding the above dataset, the description in `dataset_info.json` should be:
|
||||
|
||||
```json
|
||||
"dataset_name": {
|
||||
"file_name": "data.json",
|
||||
"columns": {
|
||||
"prompt": "text"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Remember to set `"ranking": true` for the preference datasets.
|
||||
For the **preference datasets**, the `response` column should be a string list whose length is 2, with the preferred answers appearing first, for example:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"instruction": "user instruction",
|
||||
"input": "user input",
|
||||
"output": [
|
||||
"chosen answer",
|
||||
"rejected answer"
|
||||
]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
Regarding the above dataset, the description in `dataset_info.json` should be:
|
||||
|
||||
```json
|
||||
"dataset_name": {
|
||||
"file_name": "data.json",
|
||||
"ranking": true,
|
||||
"columns": {
|
||||
"prompt": "instruction",
|
||||
"query": "input",
|
||||
"response": "output",
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
----
|
||||
|
||||
The dataset in sharegpt format should follow the below format:
|
||||
The dataset in **sharegpt** format should follow the below format:
|
||||
|
||||
```json
|
||||
[
|
||||
@ -112,10 +145,12 @@ The dataset in sharegpt format should follow the below format:
|
||||
]
|
||||
```
|
||||
|
||||
Regarding the above dataset, the `columns` in `dataset_info.json` should be:
|
||||
Regarding the above dataset, the description in `dataset_info.json` should be:
|
||||
|
||||
```json
|
||||
"dataset_name": {
|
||||
"file_name": "data.json",
|
||||
"formatting": "sharegpt",
|
||||
"columns": {
|
||||
"messages": "conversations",
|
||||
"system": "system",
|
||||
@ -132,4 +167,46 @@ Regarding the above dataset, the `columns` in `dataset_info.json` should be:
|
||||
|
||||
where the `messages` column should be a list following the `u/a/u/a/u/a` order.
|
||||
|
||||
Pre-training datasets and preference datasets are incompatible with the sharegpt format yet.
|
||||
We also supports the dataset in the **openai** format:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "system prompt (optional)"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "user instruction"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "model response"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
Regarding the above dataset, the description in `dataset_info.json` should be:
|
||||
|
||||
```json
|
||||
"dataset_name": {
|
||||
"file_name": "data.json",
|
||||
"formatting": "sharegpt",
|
||||
"columns": {
|
||||
"messages": "messages"
|
||||
},
|
||||
"tags": {
|
||||
"role_tag": "role",
|
||||
"content_tag": "content",
|
||||
"user_tag": "user",
|
||||
"assistant_tag": "assistant",
|
||||
"system_tag": "system"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Pre-training datasets and preference datasets are **incompatible** with the sharegpt format yet.
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
如果您使用自定义数据集，请务必在 `dataset_info.json` 文件中按照以下格式提供数据集定义。
|
||||
如果您使用自定义数据集，请务必按照以下格式在 `dataset_info.json` 文件中添加**数据集描述**。我们在下面也提供了一些例子。
|
||||
|
||||
```json
|
||||
"数据集名称": {
|
||||
@ -33,7 +33,7 @@
|
||||
}
|
||||
```
|
||||
|
||||
添加后可通过指定 `--dataset 数据集名称` 参数使用自定义数据集。
|
||||
然后，可通过使用 `--dataset 数据集名称` 参数加载自定义数据集。
|
||||
|
||||
----
|
||||
|
||||
@ -54,10 +54,11 @@
|
||||
]
|
||||
```
|
||||
|
||||
对于上述格式的数据，`dataset_info.json` 中的 `columns` 应为：
|
||||
对于上述格式的数据，`dataset_info.json` 中的描述应为：
|
||||
|
||||
```json
|
||||
"数据集名称": {
|
||||
"file_name": "data.json",
|
||||
"columns": {
|
||||
"prompt": "instruction",
|
||||
"query": "input",
|
||||
@ -70,28 +71,60 @@
|
||||
|
||||
其中 `query` 列对应的内容会与 `prompt` 列对应的内容拼接后作为用户指令，即用户指令为 `prompt\nquery`。`response` 列对应的内容为模型回答。
|
||||
|
||||
`system` 列对应的内容将被作为系统提示词。`history` 列是由多个字符串二元组构成的列表，分别代表历史消息中每轮的指令和回答。注意历史消息中的回答**也会被用于训练**。
|
||||
`system` 列对应的内容将被作为系统提示词。`history` 列是由多个字符串二元组构成的列表，分别代表历史消息中每轮的指令和回答。注意在指令监督学习时，历史消息中的回答**也会被用于训练**。
|
||||
|
||||
对于预训练数据集，仅 `prompt` 列中的内容会用于模型训练。
|
||||
|
||||
对于偏好数据集，`response` 列应当是一个长度为 2 的字符串列表，排在前面的代表更优的回答，例如：
|
||||
对于**预训练数据集**，仅 `prompt` 列中的内容会用于模型训练，例如：
|
||||
|
||||
```json
|
||||
{
|
||||
"instruction": "用户指令",
|
||||
"input": "用户输入",
|
||||
"output": [
|
||||
"优质回答",
|
||||
"劣质回答"
|
||||
]
|
||||
[
|
||||
{"text": "document"},
|
||||
{"text": "document"}
|
||||
]
|
||||
```
|
||||
|
||||
对于上述格式的数据，`dataset_info.json` 中的描述应为：
|
||||
|
||||
```json
|
||||
"数据集名称": {
|
||||
"file_name": "data.json",
|
||||
"columns": {
|
||||
"prompt": "text"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
添加偏好数据集需要额外指定 `"ranking": true`。
|
||||
对于**偏好数据集**，`response` 列应当是一个长度为 2 的字符串列表，排在前面的代表更优的回答，例如：
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"instruction": "用户指令",
|
||||
"input": "用户输入",
|
||||
"output": [
|
||||
"优质回答",
|
||||
"劣质回答"
|
||||
]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
对于上述格式的数据，`dataset_info.json` 中的描述应为：
|
||||
|
||||
```json
|
||||
"数据集名称": {
|
||||
"file_name": "data.json",
|
||||
"ranking": true,
|
||||
"columns": {
|
||||
"prompt": "instruction",
|
||||
"query": "input",
|
||||
"response": "output",
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
----
|
||||
|
||||
而 sharegpt 格式的数据集按照以下方式组织：
|
||||
而 **sharegpt** 格式的数据集按照以下方式组织：
|
||||
|
||||
```json
|
||||
[
|
||||
@ -112,10 +145,12 @@
|
||||
]
|
||||
```
|
||||
|
||||
对于上述格式的数据，`dataset_info.json` 中的 `columns` 应为：
|
||||
对于上述格式的数据，`dataset_info.json` 中的描述应为：
|
||||
|
||||
```json
|
||||
"数据集名称": {
|
||||
"file_name": "data.json",
|
||||
"formatting": "sharegpt",
|
||||
"columns": {
|
||||
"messages": "conversations",
|
||||
"system": "system",
|
||||
@ -132,4 +167,46 @@
|
||||
|
||||
其中 `messages` 列应当是一个列表，且符合 `用户/模型/用户/模型/用户/模型` 的顺序。
|
||||
|
||||
预训练数据集和偏好数据集尚不支持 sharegpt 格式。
|
||||
我们同样支持 **openai** 格式的数据集：
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "系统提示词（选填）"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "用户指令"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "模型回答"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
对于上述格式的数据，`dataset_info.json` 中的描述应为：
|
||||
|
||||
```json
|
||||
"数据集名称": {
|
||||
"file_name": "data.json",
|
||||
"formatting": "sharegpt",
|
||||
"columns": {
|
||||
"messages": "messages"
|
||||
},
|
||||
"tags": {
|
||||
"role_tag": "role",
|
||||
"content_tag": "content",
|
||||
"user_tag": "user",
|
||||
"assistant_tag": "assistant",
|
||||
"system_tag": "system"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
预训练数据集和偏好数据集**尚不支持** sharegpt 格式。
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user