update doc

This commit is contained in:
Xi Yan 2025-03-12 23:27:01 -07:00
parent 4cc1958af9
commit 4f6f0f6a91
3 changed files with 17 additions and 8 deletions

View file

@ -9448,7 +9448,7 @@
},
"source": {
"$ref": "#/components/schemas/DataSource",
"description": "The data source of the dataset. Examples: - { \"type\": \"uri\", \"uri\": \"https://mywebsite.com/mydata.jsonl\" } - { \"type\": \"uri\", \"uri\": \"lsfs://mydata.jsonl\" } - { \"type\": \"huggingface\", \"dataset_path\": \"tatsu-lab/alpaca\", \"params\": { \"split\": \"train\" } } - { \"type\": \"rows\", \"rows\": [ { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, world!\"}, {\"role\": \"assistant\", \"content\": \"Hello, world!\"}, ] } ] }"
"description": "The data source of the dataset. Examples: - { \"type\": \"uri\", \"uri\": \"https://mywebsite.com/mydata.jsonl\" } - { \"type\": \"uri\", \"uri\": \"lsfs://mydata.jsonl\" } - { \"type\": \"huggingface\", \"huggingface\": { \"dataset_path\": \"tatsu-lab/alpaca\", \"params\": { \"split\": \"train\" } } } - { \"type\": \"rows\", \"rows\": [ { \"messages\": [ {\"role\": \"user\", \"content\": \"Hello, world!\"}, {\"role\": \"assistant\", \"content\": \"Hello, world!\"}, ] } ] }"
},
"metadata": {
"type": "object",

View file

@ -6404,10 +6404,10 @@ components:
description: >-
The data source of the dataset. Examples: - { "type": "uri", "uri": "https://mywebsite.com/mydata.jsonl"
} - { "type": "uri", "uri": "lsfs://mydata.jsonl" } - { "type": "huggingface",
"dataset_path": "tatsu-lab/alpaca", "params": { "split": "train" } } -
{ "type": "rows", "rows": [ { "messages": [ {"role": "user", "content":
"Hello, world!"}, {"role": "assistant", "content": "Hello, world!"}, ]
} ] }
"huggingface": { "dataset_path": "tatsu-lab/alpaca", "params": { "split":
"train" } } } - { "type": "rows", "rows": [ { "messages": [ {"role": "user",
"content": "Hello, world!"}, {"role": "assistant", "content": "Hello,
world!"}, ] } ] }
metadata:
type: object
additionalProperties:

View file

@ -23,6 +23,13 @@ class DatasetPurpose(Enum):
{"role": "assistant", "content": "Hello, world!"},
]
}
:cvar eval/question-answer: The dataset contains a question and answer column.
{
"question": [
{"role": "user", "content": "What is the capital of France?"},
],
"answer": "Paris"
}
"""
post_training_messages = "post-training/messages"
@ -157,9 +164,11 @@ class Datasets(Protocol):
}
- {
"type": "huggingface",
"dataset_path": "tatsu-lab/alpaca",
"params": {
"split": "train"
"huggingface": {
"dataset_path": "tatsu-lab/alpaca",
"params": {
"split": "train"
}
}
}
- {