How to use 1kxia/gemma-3-270m-modelopt-fp8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="1kxia/gemma-3-270m-modelopt-fp8")
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("1kxia/gemma-3-270m-modelopt-fp8") model = AutoModelForCausalLM.from_pretrained("1kxia/gemma-3-270m-modelopt-fp8")
