How to use Tetsuto/gemma-3-4b-11plus-tutor with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-4b-it") model = PeftModel.from_pretrained(base_model, "Tetsuto/gemma-3-4b-11plus-tutor")
How to use Tetsuto/gemma-3-4b-11plus-tutor with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("Tetsuto/gemma-3-4b-11plus-tutor") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True)
How to use Tetsuto/gemma-3-4b-11plus-tutor with MLX LM:
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "Tetsuto/gemma-3-4b-11plus-tutor" --prompt "Once upon a time"
