feat: add sft scripts for Magicoder-Evol-Instruct-110K and alpaca-gpt4-data

- sft_magicoder.py: export ise-uiuc/Magicoder-Evol-Instruct-110K
- sft_alpaca_gpt4.py: export llm-wizard/alpaca-gpt4-data with instruction+input
- remove deprecated SFT scripts
This commit is contained in:
jiachun
2026-06-01 15:50:13 +08:00
parent e1125be3a7
commit efba7a009f
8 changed files with 38 additions and 131 deletions
@@ -0,0 +1,16 @@
from datasets import load_dataset
from pipeline import export_dataset
def process_func(input_dict: dict):
return {"query": input_dict["instruction"], "response": input_dict["response"]}
if __name__ == "__main__":
dataset = load_dataset("ise-uiuc/Magicoder-Evol-Instruct-110K")
export_dataset(
dataset=dataset["train"],
output_dir="./dataset",
output_prefix="Magicoder-Evol-Instruct-110K",
process_func=process_func,
)