{
  "_name_or_path": "TheBloke/samantha-falcon-7B-GPTQ",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "RWForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "TheBloke/samantha-falcon-7B-GPTQ--configuration_RW.RWConfig",
    "AutoModelForCausalLM": "TheBloke/samantha-falcon-7B-GPTQ--modelling_RW.RWForCausalLM"
  },
  "bias": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_dropout": 0.0,
  "hidden_size": 4544,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "RefinedWebModel",
  "multi_query": true,
  "n_head": 71,
  "n_layer": 32,
  "parallel_attn": true,
  "quantization_config": {
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": true,
    "group_size": 64,
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "sym": true,
    "true_sequential": true
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "use_cache": true,
  "vocab_size": 65024
}