gradients-io's picture
Apply YaRN extension with factor 2
937c6be verified
{
"hidden_size": 128,
"hidden_act": "gelu",
"initializer_range": 0.02,
"vocab_size": 30522,
"hidden_dropout_prob": 0.1,
"num_attention_heads": 2,
"type_vocab_size": 2,
"max_position_embeddings": 1024,
"num_hidden_layers": 2,
"intermediate_size": 512,
"attention_probs_dropout_prob": 0.1,
"rope_scaling": {
"type": "yarn",
"factor": 2.0,
"original_max_position_embeddings": 512
}
}