How to use MeridianVector/gemma3-4b-vision-gspo-lora with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MeridianVector/gemma3-4b-vision-gspo-lora", device_map="auto")
8859ad8
1
2
3
4
5
{ "image_seq_length": 256, "processor_class": "_Unsloth_Patched_Gemma3Processor" }
