YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
learning rate: 3e-5
training epochs: 5
batch size: 8
seed: 42
model: bert-base-uncased
The model is pretrained on MNLI (we use kangnichaluo/mnli-2 directly) and then finetuned on CB which is converted into two-way nli classification (predict entailment or not-entailment class)
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.