{
  "_name_or_path": "/cpfs01/shared/public/llmeval/model_weights/hf_hub/models--Qwen--Qwen2.5-72B/snapshots/91ba9841ba07ae80abda0771c034431527a5fa09",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attn_implementation": "flash_attention_2",
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 29568,
  "max_position_embeddings": 131072,
  "max_window_layers": 80,
  "model_type": "qwen2",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.0",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}