28 lines
633 B
JSON
28 lines
633 B
JSON
{
|
|
"architectures": [
|
|
"Ernie4_5ForCausalLM"
|
|
],
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1024,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 3072,
|
|
"max_position_embeddings": 131072,
|
|
"model_type": "ernie4_5",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 18,
|
|
"num_key_value_heads": 2,
|
|
"pad_token_id": 0,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 500000.0,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.54.0.dev0",
|
|
"use_bias": false,
|
|
"use_cache": true,
|
|
"vocab_size": 103424
|
|
}
|