Transformers How to use soksof/gemma-3-12b-wmt26-fp8 with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# pip install "transformers<5.0.0"
from transformers import pipeline
pipe = pipeline("translation", model="soksof/gemma-3-12b-wmt26-fp8") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("soksof/gemma-3-12b-wmt26-fp8")
model = AutoModelForCausalLM.from_pretrained("soksof/gemma-3-12b-wmt26-fp8", device_map="auto") 
