Transformers How to use ArchiveStudio/gemma-4-31B-it-assistant with Transformers:
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("ArchiveStudio/gemma-4-31B-it-assistant")
model = AutoModelForCausalLM.from_pretrained("ArchiveStudio/gemma-4-31B-it-assistant", device_map="auto") 
