config.json

{
  "_name_or_path": "microsoft/phi-4",
  "architectures": [
    "Phi3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 100257,
  "embd_pdrop": 0.0,
  "eos_token_id": 100265,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 17920,
  "max_position_embeddings": 16384,
  "model_type": "phi3",
  "neuron": {
    "auto_cast_type": "bf16",
    "batch_size": 1,
    "checkpoint_id": "microsoft/phi-4",
    "checkpoint_revision": "187ef0342fff0eb3333be9f00389385e95ef0b61",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.15.143.0+e39249ad",
    "num_cores": 2,
    "sequence_length": 2048,
    "task": "text-generation"
  },
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 10,
  "original_max_position_embeddings": 16384,
  "pad_token_id": 100349,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 250000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.3",
  "use_cache": true,
  "vocab_size": 100352
}