42 lines
1.0 KiB
JSON
42 lines
1.0 KiB
JSON
|
|
{
|
||
|
|
"_name_or_path": "Phi-tiny-MoE",
|
||
|
|
"architectures": [
|
||
|
|
"PhiMoEForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": true,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoConfig": "configuration_slimmoe.PhiMoEConfig",
|
||
|
|
"AutoModelForCausalLM": "modeling_slimmoe.PhiMoEForCausalLM"
|
||
|
|
},
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 32000,
|
||
|
|
"expert_dropout": 0.0,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_dropout": 0.0,
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"input_jitter_noise": 0.01,
|
||
|
|
"intermediate_size": 448,
|
||
|
|
"lm_head_bias": true,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"model_type": "phimoe",
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_experts_per_tok": 2,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"num_local_experts": 16,
|
||
|
|
"output_router_logits": false,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"router_aux_loss_coef": 0.0,
|
||
|
|
"router_jitter_noise": 0.01,
|
||
|
|
"sliding_window": 2047,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.43.3",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 32064
|
||
|
|
}
|