{
  "_name_or_path": "/mnt_nas/user/models/Qwen/Qwen2.5-7B-Instruct/",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "beacon_attend_previous": true,
  "beacon_attn": "step-expansion",
  "beacon_param": [
    "q",
    "k",
    "v",
    "o"
  ],
  "beacon_ratio": [
    2,
    4,
    8,
    16,
    32,
    64,
    128
  ],
  "beacon_ratio_mix": "step-random",
  "beacon_stride_mix": "step-random",
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "local_window": 3072,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "memory_stride": [
    64,
    128,
    256,
    512,
    1024,
    2048
  ],
  "model_type": "qwen2",
  "mp_layer_num": 3,
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "query_related_condensing": true,
  "retrieval_method": null,
  "retrieval_topk": 2,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "training_stage": "pretrain",
  "transformers_version": "4.39.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}