{
  "_name_or_path": "stmk_100B_2.0T_32k_mc_a_sft_d_2ep_dpo_aa_dpo_b_merged/hf_model",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "eos_token_id": 1,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 9216,
  "initializer_range": 0.02,
  "intermediate_size": 32768,
  "max_position_embeddings": 32768,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 72,
  "num_hidden_layers": 86,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.2",
  "use_cache": true,
  "vocab_size": 100352
}