|
{ |
|
"_name_or_path": "SageLite/SageLite-l", |
|
"architectures": [ |
|
"SageLite" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "config_sagelite.SageLiteConfig", |
|
"AutoTokenizer": "tokenization_sagelite.SageLiteTokenizer", |
|
"AutoModel": "modeling_sagelite.SageLiteModel", |
|
"AutoModelForMaskedLM": "modeling_sagelite.SageLiteForMaskedLM", |
|
"AutoModelForSequenceClassification": "modeling_sagelite.SageLiteForSequenceClassification" |
|
}, |
|
"activation_function": "gelu_new", |
|
"attention_dropout_prob": 0.1, |
|
"embedding_dropout_prob": 0.1, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"hidden_size": 1536, |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 24, |
|
"intermediate_size": 6144, |
|
"max_position_embeddings": 2048, |
|
"residual_dropout_prob": 0.1, |
|
"vocab_size": 100318 |
|
} |
|
|
|
|