{
  "_name_or_path": "tiiuae/falcon-40b-instruct",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "RWForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "tiiuae/falcon-40b-instruct--configuration_RW.RWConfig",
    "AutoModelForCausalLM": "tiiuae/falcon-40b-instruct--modelling_RW.RWForCausalLM"
  },
  "bias": false,
  "bos_token_id": 11,
  "eos_token_id": 11,
  "hidden_dropout": 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,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.33.0.dev0",
  "use_cache": false,
  "vocab_size": 65024
}