|
{
|
|
"activation": "gelu",
|
|
"alibi": false,
|
|
"attention_dropout": 0.0,
|
|
"bias": false,
|
|
"bos_token_id": 11,
|
|
"eos_token_id": 11,
|
|
"ffn_hidden_size": 18176,
|
|
"hidden_dropout": 0.0,
|
|
"hidden_size": 4544,
|
|
"initializer_range": 0.02,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "falcon",
|
|
"multi_query": true,
|
|
"new_decoder_architecture": false,
|
|
"num_attention_heads": 71,
|
|
"num_hidden_layers": 2,
|
|
"num_kv_heads": 71,
|
|
"parallel_attn": true,
|
|
"rope_scaling": null,
|
|
"rope_theta": 500000,
|
|
"transformers_version": "4.40.2",
|
|
"use_cache": true,
|
|
"vocab_size": 65024
|
|
}
|
|
|