{
  "architectures": [
    "Phi3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_phi3.Phi3Config",
    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
  },
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "embd_pdrop": 0.0,
  "eos_token_id": 32000,
  "hidden_act": "silu",
  "hidden_size": 3072,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 4096,
  "model_type": "phi3",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 32000,
  "partial_rotary_factor": 1.0,
  "quantization_config": {
    "config_groups": {},
    "format": "dense",
    "global_compression_ratio": null,
    "ignore": [],
    "kv_cache_scheme": {
      "actorder": null,
      "block_structure": null,
      "dynamic": false,
      "group_size": null,
      "num_bits": 8,
      "observer": "minmax",
      "observer_kwargs": {},
      "scale_dtype": null,
      "strategy": "tensor",
      "symmetric": true,
      "type": "float",
      "zp_dtype": null
    },
    "quant_method": "compressed-tensors",
    "quantization_status": "frozen",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.3.a20251114"
  },
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "sliding_window": 2047,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 32064
}