|
{ |
|
"architectures": [ |
|
"Ernie4_5_MoeForCausalLM" |
|
], |
|
"bos_token_id": 1, |
|
"dtype": "bfloat16", |
|
"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_capacity": [ |
|
64, |
|
64, |
|
64 |
|
], |
|
"moe_gate": "top2_fused", |
|
"moe_intermediate_size": 1536, |
|
"moe_k": 6, |
|
"moe_layer_end_index": 47, |
|
"moe_layer_interval": 1, |
|
"moe_layer_start_index": 1, |
|
"moe_norm_min": 1e-12, |
|
"moe_num_experts": 64, |
|
"moe_num_shared_experts": 2, |
|
"moe_use_aux_free": true, |
|
"num_attention_heads": 20, |
|
"num_hidden_layers": 47, |
|
"num_key_value_heads": 4, |
|
"output_router_logits": false, |
|
"pad_token_id": 0, |
|
"quantization": { |
|
"group_size": 32, |
|
"bits": 4, |
|
"mode": "mxfp4" |
|
}, |
|
"quantization_config": { |
|
"group_size": 32, |
|
"bits": 4, |
|
"mode": "mxfp4" |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 500000, |
|
"router_aux_loss_coef": 0.001, |
|
"tie_word_embeddings": false, |
|
"transformers_version": "4.56.1", |
|
"use_bias": false, |
|
"use_cache": true, |
|
"vocab_size": 103424 |
|
} |
|
|