config.json

{
  "_name_or_path": "microsoft/Phi-3.5-MoE-instruct",
  "architectures": [
    "PhiMoEForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_phimoe.PhiMoEConfig",
    "AutoModelForCausalLM": "modeling_phimoe.PhiMoEForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 32000,
  "hidden_act": "silu",
  "hidden_dropout": 0.0,
  "hidden_size": 16,
  "initializer_range": 0.02,
  "input_jitter_noise": 0.01,
  "intermediate_size": 32,
  "lm_head_bias": true,
  "max_position_embeddings": 131072,
  "model_type": "phimoe",
  "num_attention_heads": 4,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 4,
  "num_local_experts": 16,
  "original_max_position_embeddings": 4096,
  "output_router_logits": false,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1.0299,
      1.0499
    ],
    "long_mscale": 1.243163121016122,
    "original_max_position_embeddings": 4096,
    "short_factor": [
      1.05,
      1.05
    ],
    "short_mscale": 1.243163121016122,
    "type": "longrope"
  },
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.0,
  "router_jitter_noise": 0.01,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.0",
  "use_cache": true,
  "vocab_size": 32064
}