distilbert-base-fa / config.yaml
arxyzan's picture
Update config.yaml
fb9f7d6
raw
history blame
No virus
329 Bytes
name: distilbert_lm
config_type: model
task: language_modeling
activation: gelu
attention_dropout: 0.1
dim: 768
dropout: 0.1
hidden_dim: 3072
initializer_range: 0.02
max_position_embeddings: 512
model_type: distilbert
n_heads: 12
n_layers: 6
output_past: true
pad_token_id: 0
qa_dropout: 0.1
tie_weights_: true
vocab_size: 42000