{
  "_name_or_path": "tiiuae/falcon-40b",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "RWForCausalLM"
  ],
  "attention_dropout": 0.0,
  "attention_probs_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "tiiuae/falcon-40b--configuration_RW.RWConfig",
    "AutoModel": "tiiuae/falcon-40b--modelling_RW.RWModel",
    "AutoModelForCausalLM": "tiiuae/falcon-40b--modelling_RW.RWForCausalLM",
    "AutoModelForQuestionAnswering": "tiiuae/falcon-40b--modelling_RW.RWForQuestionAnswering",
    "AutoModelForSequenceClassification": "tiiuae/falcon-40b--modelling_RW.RWForSequenceClassification",
    "AutoModelForTokenClassification": "tiiuae/falcon-40b--modelling_RW.RWForTokenClassification"
  },
  "bias": false,
  "bos_token_id": 11,
  "custom_pipelines": {
    "text-generation": {
      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
      "pt": "AutoModelForCausalLM"
    }
  },
  "eos_token_id": 11,
  "hidden_dropout": 0.0,
  "hidden_dropout_prob": 0.0,
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "RefinedWeb",
  "n_head": 128,
  "n_head_kv": 8,
  "n_layer": 60,
  "parallel_attn": true,
  "torch_dtype": "float16",
  "transformers_version": "4.29.0",
  "use_cache": true,
  "vocab_size": 65024,
  "quantization_config": {
    "bits": 4,
    "group_size": -1,
    "damp_percent": 0.01,
    "desc_act": true,
    "sym": true,
    "true_sequential": true,
    "model_name_or_path": null,
    "model_file_base_name": "model",
    "quant_method": "gptq"
  }
}