How to use prometheus-eval/prometheus-vision-7b-v1.0 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="prometheus-eval/prometheus-vision-7b-v1.0")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("prometheus-eval/prometheus-vision-7b-v1.0") model = AutoModelForCausalLM.from_pretrained("prometheus-eval/prometheus-vision-7b-v1.0", device_map="auto")
https://huggingface.co/prometheus-eval/prometheus-vision-7b-v1.0/resolve/main/perception_collection.png
hf download hf://prometheus-eval/prometheus-vision-7b-v1.0/perception_collection.png
curl -L -o perception_collection.png https://huggingface.co/prometheus-eval/prometheus-vision-7b-v1.0/resolve/main/perception_collection.png
