How to use Swicked86/phi4-mm-gptq with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="Swicked86/phi4-mm-gptq", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Swicked86/phi4-mm-gptq", trust_remote_code=True, device_map="auto")
https://huggingface.co/Swicked86/phi4-mm-gptq/resolve/main/processor_config.json
hf download hf://Swicked86/phi4-mm-gptq/processor_config.json
curl -L -o processor_config.json https://huggingface.co/Swicked86/phi4-mm-gptq/resolve/main/processor_config.json
