|
{
|
|
"_name_or_path": "./checkpoint-10000",
|
|
"architectures": [
|
|
"DogeForCausalLM"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_doge.DogeConfig",
|
|
"AutoModelForCausalLM": "modeling_doge.DogeForCausalLM"
|
|
},
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_bias": false,
|
|
"hidden_dropout": 0.0,
|
|
"hidden_size": 512,
|
|
"initializer_range": 0.02,
|
|
"inner_values_retrieval_size": 128,
|
|
"intermediate_size": 2048,
|
|
"max_position_embeddings": 4096,
|
|
"model_type": "doge",
|
|
"num_attention_heads": 4,
|
|
"num_cdmmoe_experts": 2048,
|
|
"num_cdmmoe_experts_per_head": 4,
|
|
"num_cdmmoe_heads": 2,
|
|
"num_hidden_layers": 8,
|
|
"num_inner_value_heads": 2,
|
|
"num_inner_values": 4,
|
|
"num_value_per_head": 2,
|
|
"pad_token_id": 0,
|
|
"private_expert_retrieval_size": 256,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.46.1",
|
|
"use_cache": true,
|
|
"vocab_size": 32768
|
|
}
|
|
|