How to use gpol13/gemma3_sparse_lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-it") model = PeftModel.from_pretrained(base_model, "gpol13/gemma3_sparse_lora")
https://huggingface.co/gpol13/gemma3_sparse_lora/resolve/main/tokenizer_config.json
hf download hf://gpol13/gemma3_sparse_lora/tokenizer_config.json
curl -L -o tokenizer_config.json https://huggingface.co/gpol13/gemma3_sparse_lora/resolve/main/tokenizer_config.json
