How to use coolthor/gemma-4-12B-it-FP8-dynamic with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("coolthor/gemma-4-12B-it-FP8-dynamic") model = AutoModelForMultimodalLM.from_pretrained("coolthor/gemma-4-12B-it-FP8-dynamic", device_map="auto")
Thanks @Sidd065 — this is already applied directly from upstream in 425ac4c8 (byte-identical to your PR, kept the trailing newline to match google/gemma-4-12B-it exactly), so I'm closing this. Appreciate you sending it! 🙏
425ac4c8
· Sign up or log in to comment
