How to use marmalade/efficient-splade-VI-BT-large-query with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="marmalade/efficient-splade-VI-BT-large-query")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("marmalade/efficient-splade-VI-BT-large-query") model = AutoModelForMaskedLM.from_pretrained("marmalade/efficient-splade-VI-BT-large-query", device_map="auto")
https://huggingface.co/marmalade/efficient-splade-VI-BT-large-query/resolve/main/special_tokens_map.json
hf download hf://marmalade/efficient-splade-VI-BT-large-query/special_tokens_map.json
curl -L -o special_tokens_map.json https://huggingface.co/marmalade/efficient-splade-VI-BT-large-query/resolve/main/special_tokens_map.json
