The dataset_info.json contains all available datasets. If you are using a custom dataset, please make sure to add a dataset description in dataset_info.json and specify dataset: dataset_name before training to use it.
Currently we support datasets in alpaca and sharegpt format.
"dataset_name": {
"hf_hub_url": "the name of the dataset repository on the Hugging Face hub. (if specified, ignore script_url and file_name)",
"ms_hub_url": "the name of the dataset repository on the Model Scope hub. (if specified, ignore script_url and file_name)",
"script_url": "the name of the directory containing a dataset loading script. (if specified, ignore file_name)",
"file_name": "the name of the dataset folder or dataset file in this directory. (required if above are not specified)",
"formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
"ranking": "whether the dataset is a preference dataset or not. (default: False)",
"subset": "the name of the subset. (optional, default: None)",
"split": "the name of dataset split to be used. (optional, default: train)",
"folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
"num_samples": "the number of samples in the dataset to be used. (optional, default: None)",
"columns (optional)": {
"prompt": "the column name in the dataset containing the prompts. (default: instruction)",
"query": "the column name in the dataset containing the queries. (default: input)",
"response": "the column name in the dataset containing the responses. (default: output)",
"history": "the column name in the dataset containing the histories. (default: None)",
"messages": "the column name in the dataset containing the messages. (default: conversations)",
"system": "the column name in the dataset containing the system prompts. (default: None)",
"tools": "the column name in the dataset containing the tool description. (default: None)",
"images": "the column name in the dataset containing the image inputs. (default: None)",
"videos": "the column name in the dataset containing the videos inputs. (default: None)",
"chosen": "the column name in the dataset containing the chosen answers. (default: None)",
"rejected": "the column name in the dataset containing the rejected answers. (default: None)",
"kto_tag": "the column name in the dataset containing the kto tags. (default: None)"
},
"tags (optional, used for the sharegpt format)": {
"role_tag": "the key in the message represents the identity. (default: from)",
"content_tag": "the key in the message represents the content. (default: value)",
"user_tag": "the value of the role_tag represents the user. (default: human)",
"assistant_tag": "the value of the role_tag represents the assistant. (default: gpt)",
"observation_tag": "the value of the role_tag represents the tool results. (default: observation)",
"function_tag": "the value of the role_tag represents the function call. (default: function_call)",
"system_tag": "the value of the role_tag represents the system prompt. (default: system, can override system column)"
}
}In supervised fine-tuning, the instruction column will be concatenated with the input column and used as the human prompt, then the human prompt would be instruction\ninput. The output column represents the model response.
The system column will be used as the system prompt if specified.
The history column is a list consisting of string tuples representing prompt-response pairs in the history messages. Note that the responses in the history will also be learned by the model in supervised fine-tuning.
[
{
"instruction": "human instruction (required)",
"input": "human input (optional)",
"output": "model response (required)",
"system": "system prompt (optional)",
"history": [
["human instruction in the first round (optional)", "model response in the first round (optional)"],
["human instruction in the second round (optional)", "model response in the second round (optional)"]
]
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"system": "system",
"history": "history"
}
}In pre-training, only the text column will be used for model learning.
[
{"text": "document"},
{"text": "document"}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"columns": {
"prompt": "text"
}
}Preference datasets are used for reward modeling, DPO training, ORPO and SimPO training.
It requires a better response in chosen column and a worse response in rejected column.
[
{
"instruction": "human instruction (required)",
"input": "human input (optional)",
"chosen": "chosen answer (required)",
"rejected": "rejected answer (required)"
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"ranking": true,
"columns": {
"prompt": "instruction",
"query": "input",
"chosen": "chosen",
"rejected": "rejected"
}
}An additional column kto_tag is required. Please refer to the sharegpt format for details.
An additional column images is required. Please refer to the sharegpt format for details.
An additional column videos is required. Please refer to the sharegpt format for details.
Compared to the alpaca format, the sharegpt format allows the datasets have more roles, such as human, gpt, observation and function. They are presented in a list of objects in the conversations column.
Note that the human and observation should appear in odd positions, while gpt and function should appear in even positions.
[
{
"conversations": [
{
"from": "human",
"value": "human instruction"
},
{
"from": "function_call",
"value": "tool arguments"
},
{
"from": "observation",
"value": "tool result"
},
{
"from": "gpt",
"value": "model response"
}
],
"system": "system prompt (optional)",
"tools": "tool description (optional)"
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"system": "system",
"tools": "tools"
}
}Not yet supported, please use the alpaca format.
Preference datasets in sharegpt format also require a better message in chosen column and a worse message in rejected column.
[
{
"conversations": [
{
"from": "human",
"value": "human instruction"
},
{
"from": "gpt",
"value": "model response"
},
{
"from": "human",
"value": "human instruction"
}
],
"chosen": {
"from": "gpt",
"value": "chosen answer (required)"
},
"rejected": {
"from": "gpt",
"value": "rejected answer (required)"
}
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"ranking": true,
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected"
}
}KTO datasets require a extra kto_tag column containing the boolean human feedback.
[
{
"conversations": [
{
"from": "human",
"value": "human instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"kto_tag": "human feedback [true/false] (required)"
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"kto_tag": "kto_tag"
}
}Multimodal image datasets require a images column containing the paths to the input images.
The number of images should be identical to the <image> tokens in the conversations.
[
{
"conversations": [
{
"from": "human",
"value": "<image>human instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"images": [
"image path (required)"
]
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"images": "images"
}
}Multimodal video datasets require a videos column containing the paths to the input videos.
The number of videos should be identical to the <video> tokens in the conversations.
[
{
"conversations": [
{
"from": "human",
"value": "<video>human instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"videos": [
"video path (required)"
]
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"videos": "videos"
}
}The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.
[
{
"messages": [
{
"role": "system",
"content": "system prompt (optional)"
},
{
"role": "user",
"content": "human instruction"
},
{
"role": "assistant",
"content": "model response"
}
]
}
]Regarding the above dataset, the dataset description in dataset_info.json should be:
"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"
}
}