|
{ |
|
"architectures": [ |
|
"LtgbertFoCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "configuration_ltgbert.LtgbertConfig", |
|
"AutoModel": "modeling_ltgbert.LtgbertModel", |
|
"AutoModelForCausalLM": "modeling_ltgbert.LtgbertForCausalLM", |
|
"AutoModelForMaskedLM": "modeling_ltgbert.LtgbertForMaskedLM", |
|
"AutoModelForSequenceClassification": "modeling_ltgbert.LtgbertForSequenceClassification", |
|
"AutoModelForTokenClassification": "modeling_ltgbert.LtgbertForTokenClassification", |
|
"AutoModelForQuestionAnswering": "modeling_ltgbert.LtgbertForQuestionAnswering", |
|
"AutoModelForMultipleChoice": "modeling_ltgbert.LtgbertForMultipleChoice" |
|
}, |
|
"attention_probs_dropout_prob": 0.1, |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 384, |
|
"intermediate_size": 1280, |
|
"layer_norm_eps": 1e-07, |
|
"max_position_embeddings": 512, |
|
"num_attention_heads": 6, |
|
"num_hidden_layers": 12, |
|
"position_bucket_size": 32, |
|
"torch_dtype": "float32", |
|
"vocab_size": 8192, |
|
"temperature": 2.65 |
|
} |