{
  "_name_or_path": "/bask/homes/u/usjs9456/ai_workloads_project/S1_workspace/experiments/trainning/qwen2.5_1.5B_instruct_4H100_S1.1_GAS1/ckpts/s1.1_20250327_175558",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "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": "float32",
  "transformers_version": "4.46.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}