{
  "architectures": [
    "PawLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "disable_linear_regularization_term": false,
  "enable_ada_sparsity": true,
  "enable_lambda_task": true,
  "enable_layerwise_sparsity": false,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "erank_analysis_path": "/",
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "layerwise_sparsity_max_ratio": 1.0,
  "layerwise_sparsity_min_ratio": 0.5,
  "layerwise_sparsity_power": 1.0,
  "layerwise_sparsity_schedule": "high-low-high",
  "layerwise_sparsity_weight": 1.0,
  "local_window_size": 2048,
  "max_position_embeddings": 262144,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "pooling_mode": "ctx_q",
  "pooling_seq": true,
  "pretraining_tp": 1,
  "retrieval_mode": "full",
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "sink_size": 128,
  "suggested_sparsity": null,
  "suggested_threshold": 0.46259092167019844,
  "tie_word_embeddings": false,
  "toggle_type": "xattn",
  "topk_k": 2048,
  "torch_dtype": "float32",
  "transformers_version": "4.51.1",
  "triangle_n_last": 128,
  "use_cache": true,
  "use_softmax": true,
  "use_task_emb_for_mask": false,
  "vocab_size": 128256
}