mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-20 06:12:07 +00:00
bab02ff2bc
* feat: add ruff and resolve issue * fix: update client exports and adjust after rebase * fix: adjust syntax to avoid circular import * fix: adjust client ruff settings * fix: lint and refactor import check and avoid model enum as global names * fix: improve fbgemm_gpu check and lints * fix: update lints * fix: prefer comparing model enum over str * fix: adjust lints and ignore specific rules * fix: avoid unneeded quantize check
28 lines
701 B
Python
28 lines
701 B
Python
import json
|
|
import datasets
|
|
import tqdm
|
|
|
|
|
|
def main():
|
|
dataset = datasets.load_dataset("Open-Orca/OpenOrca", split="train")
|
|
# Select only the first 2k conversations that start with a human.
|
|
max = min(2000, len(dataset))
|
|
conversations = []
|
|
for item in tqdm.tqdm(dataset, total=max):
|
|
conversation = {
|
|
"conversations": [
|
|
{"from": "human", "value": item["question"]},
|
|
],
|
|
"id": item["id"],
|
|
}
|
|
conversations.append(conversation)
|
|
if len(conversations) >= max:
|
|
break
|
|
|
|
with open("./small.json", "w") as f:
|
|
json.dump(conversations, f, indent=4)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|