32 lines
822 B
JSON
32 lines
822 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"KeuralMoECausalLM"
|
||
|
|
],
|
||
|
|
"model_type": "keural",
|
||
|
|
"vocab_size": 131074,
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"intermediate_size": 5632,
|
||
|
|
"num_hidden_layers": 24,
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"head_dim": 128,
|
||
|
|
"num_local_experts": 8,
|
||
|
|
"num_experts_per_tok": 2,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"rope_theta": 500000.0,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"sliding_window": 512,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"use_cache": true,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.40.0",
|
||
|
|
"output_router_logits": false,
|
||
|
|
"router_aux_loss_coef": 0.001,
|
||
|
|
"keural_step": 5500,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration_keural.KeuralConfig",
|
||
|
|
"AutoModelForCausalLM": "modeling_keural.KeuralMoECausalLM"
|
||
|
|
}
|
||
|
|
}
|