Transformers
Back to all models
Model: unilm-base-cased

Monthly model downloads

unilm-base-cased unilm-base-cased
- downloads
last 30 days

How to use this model directly from the πŸ€—/transformers library:

			
Copy model
tokenizer = AutoTokenizer.from_pretrained("unilm-base-cased") model = AutoModel.from_pretrained("unilm-base-cased")

Config

See raw config file
attention_probs_dropout_prob: 0.1 ...
directionality: "bidi" ...
hidden_act: "gelu" ...
hidden_dropout_prob: 0.1 ...
hidden_size: 768 ...
initializer_range: 0.02 ...
intermediate_size: 3072 ...
max_position_embeddings: 512 ...
num_attention_heads: 12 ...
num_hidden_layers: 12 ...
pooler_fc_size: 768 ...
pooler_num_attention_heads: 12 ...
pooler_num_fc_layers: 3 ...
pooler_size_per_head: 128 ...
pooler_type: "first_token_transform" ...
type_vocab_size: 6 ...
layer_norm_epsilon: 0.00001 ...
vocab_size: 28996 ...
label_smoothing: 0 ...