config.json

{
  "_name_or_path": "meta-llama/Llama-2-7b-hf",
  "architectures": [
    "SparseLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "ugly_utils.SparseLlamaConfig",
    "AutoModelForCausalLM": "ugly_utils.SparseLlamaForCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "model_type": "sparse_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "thresholds": [
    0.01905716396868229,
    0.03510531038045883,
    0.049147434532642365,
    0.061183542013168335,
    0.07923770695924759,
    0.09327983111143112,
    0.10932797938585281,
    0.11735205352306366,
    0.11935807019472122,
    0.12337010353803635,
    0.1253761202096939,
    0.12738214433193207,
    0.12738214433193207,
    0.1313941776752472,
    0.13340020179748535,
    0.13941824436187744,
    0.14744232594966888,
    0.151454359292984,
    0.15546639263629913,
    0.15546639263629913,
    0.16349045932292938,
    0.16349045932292938,
    0.1675025075674057,
    0.1675025075674057,
    0.17151454091072083,
    0.1735205501317978,
    0.1775325983762741,
    0.18154463171958923,
    0.1835506409406662,
    0.18555666506290436,
    0.19157472252845764,
    0.19558675587177277
  ],
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.2",
  "us_sparse_regularization": false,
  "use_cache": false,
  "use_graceful_regularization": false,
  "use_relu": false,
  "use_sparse_model": true,
  "use_sparse_predictor": false,
  "use_sparse_regularization": false,
  "vocab_size": 32000
}