|
{ |
|
"architectures": [ |
|
"PanguProMoEForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "configuration_pangu_moe.PanguProMoEConfig", |
|
"AutoModel": "modeling_pangu_moe.PanguProMoEModel", |
|
"AutoModelForCausalLM": "modeling_pangu_moe.PanguProMoEForCausalLM" |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": 45892, |
|
"hidden_act": "silu", |
|
"hidden_size": 5120, |
|
"initializer_range": 0.02, |
|
"max_position_embeddings": 131072, |
|
"model_type": "PanguProMoE", |
|
"moe_intermediate_size": 1344, |
|
"num_attention_heads": 40, |
|
"num_experts": 64, |
|
"num_experts_per_tok": 8, |
|
"num_hidden_layers": 48, |
|
"num_key_value_heads": 8, |
|
"output_router_logits": false, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 16000000.0, |
|
"router_aux_loss_coef": 0.001, |
|
"shared_expert_intermediate_size": 5376, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.48.2", |
|
"use_cache": true, |
|
"vocab_size": 153376 |
|
} |
|
|