Table Understanding
Collection
4 items • Updated • 1
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("pkupie/ProTrix")
model = AutoModelForCausalLM.from_pretrained("pkupie/ProTrix")This model is described in the paper ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("table-question-answering", model="pkupie/ProTrix")