How to use trl-lib/Qwen2-0.5B-Reward-Math-Sheperd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="trl-lib/Qwen2-0.5B-Reward-Math-Sheperd")
# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("trl-lib/Qwen2-0.5B-Reward-Math-Sheperd") model = AutoModelForTokenClassification.from_pretrained("trl-lib/Qwen2-0.5B-Reward-Math-Sheperd")
I think model need to train at least for 1 epoch. anyhow, great work.
· Sign up or log in to comment
