How to use codeShare/gemma-4-E2B-it-heretic-image-caption-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("coder3101/gemma-4-E2B-it-heretic") model = PeftModel.from_pretrained(base_model, "codeShare/gemma-4-E2B-it-heretic-image-caption-adapter")
How to use codeShare/gemma-4-E2B-it-heretic-image-caption-adapter with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="codeShare/gemma-4-E2B-it-heretic-image-caption-adapter")
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("codeShare/gemma-4-E2B-it-heretic-image-caption-adapter", device_map="auto")
