Sharded checkpoints
Collection
useful sharded checkpoints for users to run inference / fine-tuning on a Google colab without having to deal with CPU OOM issues. β’ 7 items β’ Updated β’ 4
How to use ybelkada/blip2-opt-2.7b-fp16-sharded 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="ybelkada/blip2-opt-2.7b-fp16-sharded") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("ybelkada/blip2-opt-2.7b-fp16-sharded")
model = AutoModelForMultimodalLM.from_pretrained("ybelkada/blip2-opt-2.7b-fp16-sharded", device_map="auto")No model card