synthetic_data_deepseekr1_qwen_distill.py

# /// script
# requires-python = ">=3.11,<3.12"
# dependencies = [
#     "distilabel[hf-transformers, hf-inference-endpoints]",
# ]
# ///
from distilabel.models import InferenceEndpointsLLM
from distilabel.pipeline import InstructionResponsePipeline

repo_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
llm = InferenceEndpointsLLM(
    model_id=repo_id,
    tokenizer_id=repo_id,
    magpie_pre_query_template="<｜begin▁of▁sentence｜>User: ",
    use_magpie_template=True,
)
pipeline = InstructionResponsePipeline(llm=llm, batch_size=5, num_rows=10)

if __name__ == "__main__":
    dataset = pipeline.run()
    dataset.push_to_hub("davidberenstein1957/sft-dataset")