# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("UnlikelyAI/crossencoder-wiki-large-ft-k10-0.2test-b1g8-e2")
model = AutoModelForMaskedLM.from_pretrained("UnlikelyAI/crossencoder-wiki-large-ft-k10-0.2test-b1g8-e2")Quick Links
Fine-Tuned BLINK CrossEncoder.
- Base model: https://huggingface.co/UnlikelyAI/crossencoder-wiki-large
- Training data:
- 20% (stratified by source dataset) of the following entity resolution benchmarks:
- handwritten_entity_linking
- wikibank_entity_linking
- kilt_entity_linking
- jobe_entity_linking
- qald9_entity_linking
- 20% (stratified by source dataset) of the following entity resolution benchmarks:
- Training setup:
- 1 L4 GPU (23GB)
- batch_size = 1
- gradient_accumulation_steps = 8
- type_optimization = "all_encoder_layers" (i.e. ["additional", "bert_model.encoder.layer"])
- n_epochs = 2
- Downloads last month
- 8
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="UnlikelyAI/crossencoder-wiki-large-ft-k10-0.2test-b1g8-e2")