afaji's picture
fresh-2-layer-arc2000-distill-of-fresh-2-layer-gpqa_EVAL_gpqa
3aeb7b3 verified
raw
history blame contribute delete
598 Bytes
{
"architectures": [
"BertForMultipleChoice"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 8,
"num_hidden_layers": 2,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.34.0.dev0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}