How to use yujiepan/bert-base-uncased-sst2-NNCF-unstructured-sparse-80 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="yujiepan/bert-base-uncased-sst2-NNCF-unstructured-sparse-80")
# Load model directly from transformers import AutoTokenizer, NNCFNetwork tokenizer = AutoTokenizer.from_pretrained("yujiepan/bert-base-uncased-sst2-NNCF-unstructured-sparse-80") model = NNCFNetwork.from_pretrained("yujiepan/bert-base-uncased-sst2-NNCF-unstructured-sparse-80", device_map="auto")
This model is trained with magnitude sparsity on SST-2 using NNCF. The "pytorch_model.bin" contains customized components needed by NNCF. Accuracy: 0.9128440366972477
Files info
