37 lines
905 B
JSON
37 lines
905 B
JSON
{
|
|
"architectures": [
|
|
"Ernie4_5_MoeForCausalLM"
|
|
],
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2560,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 12288,
|
|
"max_position_embeddings": 131072,
|
|
"model_type": "ernie4_5_moe",
|
|
"moe_intermediate_size": 1536,
|
|
"moe_k": 6,
|
|
"moe_layer_end_index": 27,
|
|
"moe_layer_interval": 1,
|
|
"moe_layer_start_index": 1,
|
|
"moe_norm_min": 1e-12,
|
|
"moe_num_experts": 64,
|
|
"moe_num_shared_experts": 2,
|
|
"num_attention_heads": 20,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 4,
|
|
"num_nextn_predict_layers": 1,
|
|
"output_router_logits": false,
|
|
"pad_token_id": 0,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 500000.0,
|
|
"router_aux_loss_coef": 0.001,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.54.0.dev0",
|
|
"use_bias": false,
|
|
"use_cache": true,
|
|
"vocab_size": 103424
|
|
}
|