{
  "_name_or_path": "/scratch/tikhomirov/workdir/data/models/ruadapt_qwen2.5_1.5B_ext_u48_part1-2_lr5e4_bs128_reinit_peft_mlp_32_128_lm_head_mts_1e4_as1.75_v1/sft1",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "eos_token_id": 145111,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 145152
}