How to use google-t5/t5-11b with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" 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("translation", model="google-t5/t5-11b")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("google-t5/t5-11b") model = AutoModelWithLMHead.from_pretrained("google-t5/t5-11b", device_map="auto")
https://huggingface.co/google-t5/t5-11b/resolve/main/spiece.model
hf download hf://google-t5/t5-11b/spiece.model
curl -L -o spiece.model https://huggingface.co/google-t5/t5-11b/resolve/main/spiece.model
