config.json

{
  "architectures": [
    "Phi3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_phi3.Phi3Config",
    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
    "AutoTokenizer": "Xenova/gpt-4o"
  },
  "bos_token_id": 199999,
  "embd_pdrop": 0.0,
  "eos_token_id": 199999,
  "full_attn_mod": 1,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.1,
  "intermediate_size": 256,
  "interpolate_factor": 1,
  "lm_head_bias": false,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "phi3",
  "num_attention_heads": 4,
  "num_hidden_layers": 4,
  "num_key_value_heads": 2,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 199999,
  "partial_rotary_factor": 0.75,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1,
      2.446418898,
      5.984965424,
      14.64173252,
      32.1,
      32.71
    ],
    "short_factor": [
      1.0,
      1.0,
      1.0,
      1.0,
      1.0,
      1.0
    ],
    "type": "longrope"
  },
  "rope_theta": 10000.0,
  "sliding_window": 262144,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.4",
  "use_cache": true,
  "vocab_size": 200064
}