How to use Kkordik/test_longformer_4096_qsi with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "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("question-answering", model="Kkordik/test_longformer_4096_qsi")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Kkordik/test_longformer_4096_qsi") model = AutoModelForQuestionAnswering.from_pretrained("Kkordik/test_longformer_4096_qsi", device_map="auto")
https://huggingface.co/Kkordik/test_longformer_4096_qsi/resolve/4389ada96f1169d2a3f7158d5a5c03a6052b260b/tokenizer.json
hf download hf://Kkordik/test_longformer_4096_qsi@4389ada96f1169d2a3f7158d5a5c03a6052b260b/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/Kkordik/test_longformer_4096_qsi/resolve/4389ada96f1169d2a3f7158d5a5c03a6052b260b/tokenizer.json
