How to use wls04/math_bi7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="wls04/math_bi7b")
# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("wls04/math_bi7b") model = AutoModelForTokenClassification.from_pretrained("wls04/math_bi7b", device_map="auto")
