config.json

{
  "_name_or_path": "/scr/jay/ckpt/Mistral_Sparse_refined_web_50p",
  "architectures": [
    "SparseMistralforCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "sparsification_sftt.SparseMistralConfig",
    "AutoModelForCausalLM": "sparsification_sftt.SparseMistralforCausalLM"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "sparse_mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "thresholds": [
    0.023069201037287712,
    0.03309928998351097,
    0.04312938079237938,
    0.05516548827290535,
    0.07522567361593246,
    0.09327983111143112,
    0.10531593859195709,
    0.11935807019472122,
    0.12738214433193207,
    0.12738214433193207,
    0.1313941776752472,
    0.13340020179748535,
    0.13941824436187744,
    0.1414242684841156,
    0.15546639263629913,
    0.1675025075674057,
    0.18555666506290436,
    0.19157472252845764,
    0.20762285590171814,
    0.2196589708328247,
    0.22768303751945496,
    0.23771312832832336,
    0.2357071191072464,
    0.23771312832832336,
    0.24172517657279968,
    0.24172517657279968,
    0.24172517657279968,
    0.24172517657279968,
    0.24172517657279968,
    0.23971915245056152,
    0.2357071191072464,
    0.225677028298378
  ],
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.2",
  "use_cache": false,
  "use_relu": false,
  "use_sparse_model": true,
  "use_sparse_predictor": false,
  "use_sparse_regularization": false,
  "vocab_size": 32000
}