{
  "_name_or_path": "/home/jzhanggr/LMFlow_0110/LMFlow/output_models/math_ft_phi2_orca",
  "activation_function": "gelu_new",
  "architectures": [
    "PhiForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attn_pdrop": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_phi.PhiConfig",
    "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
  },
  "bos_token_id": 1,
  "embd_pdrop": 0.0,
  "eos_token_id": 2,
  "flash_attn": false,
  "flash_rotary": false,
  "fused_dense": false,
  "hidden_act": "gelu_new",
  "hidden_size": 2048,
  "img_processor": null,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "layer_norm_eps": 1e-05,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "phi",
  "n_embd": 2560,
  "n_head": 32,
  "n_head_kv": null,
  "n_inner": null,
  "n_layer": 32,
  "n_positions": 2048,
  "num_attention_heads": 32,
  "num_hidden_layers": 24,
  "num_key_value_heads": 32,
  "partial_rotary_factor": 0.5,
  "qk_layernorm": false,
  "resid_pdrop": 0.1,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "rotary_dim": 32,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 51200
}