Tiny reward models
Collection
4 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Qwen3ForSequenceClassification")
model = AutoModelForSequenceClassification.from_pretrained("trl-internal-testing/tiny-Qwen3ForSequenceClassification")This is a minimal model built for unit tests in the TRL library.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="trl-internal-testing/tiny-Qwen3ForSequenceClassification")