config.json

{
  "_name_or_path": "/home/mkurman/gitlab/ai/model-trainer/results/phi-4/2025-01-09 18_14_41/final",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {},
  "bos_token_id": 100257,
  "embd_pdrop": 0.0,
  "eos_token_id": [
    100257,
    100265
  ],
  "hdic_topk": 8,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 10752,
  "max_position_embeddings": 16384,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 40,
  "num_hidden_layers": 40,
  "num_key_value_heads": 10,
  "original_max_position_embeddings": 16384,
  "pad_token_id": 100257,
  "pretraining_tp": 1,
  "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": "4.46.2",
  "use_cache": true,
  "vocab_size": 100352
}