Tom Aarsen tomaarsen

Sentence Transformers, SetFit & NLTK maintainer, ML Engineer & Fellow @ 🤗Hugging Face

tomaarsen / train_script.py

Created July 9, 2025 13:00

Boilerplate to train a reranker model using Sentence Transformers

	import logging
	import traceback

	import torch
	from datasets import load_dataset

	from sentence_transformers import SentenceTransformer
	from sentence_transformers.cross_encoder import (
	CrossEncoder,
	CrossEncoderModelCardData,

tomaarsen / train_script.py

Created August 28, 2025 14:30

MS MARCO Contrastive and/or Distillation sample training script

	import argparse
	import logging
	import traceback
	from collections import defaultdict
	from collections.abc import Iterable
	from enum import Enum, auto

	import torch
	from datasets import load_dataset
	from torch import Tensor

tomaarsen / update_e5_nl.py

Created September 24, 2025 16:08

Script to update all E5-NL models to be nicely integrated with Sentence Transformers

	import re
	from huggingface_hub import get_collection, ModelCard
	from sentence_transformers import SentenceTransformer
	from sentence_transformers.models import Normalize

	collection = get_collection(collection_slug="clips/e5-nl-68be9d3760240ce5c7d9f831")

	ST_SNIPPET_PATTERN = r"""\
	from sentence_transformers import SentenceTransformer
	model = SentenceTransformer\((?:'\|")([a-zA-Z0-9_\/\.-]+?)(?:'\|")\)