text_model_cfg.json

{
    "_name_or_path": "microsoft/phi-1_5",
    "activation_function": "gelu_new",
    "architectures": [
        "PhiForCausalLM"
    ],
    "attn_pdrop": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_phi.PhiConfig",
        "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
    },
    "embd_pdrop": 0.0,
    "flash_attn": false,
    "flash_rotary": false,
    "fused_dense": false,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "model_type": "phi-msft",
    "n_embd": 2048,
    "n_head": 32,
    "n_head_kv": null,
    "n_inner": null,
    "n_layer": 24,
    "n_positions": 2048,
    "resid_pdrop": 0.0,
    "rotary_dim": 32,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.34.1",
    "vocab_size": 51200
}