{
  "_name_or_path": "tiiuae/falcon-40b-instruct",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "FalconForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "tiiuae/falcon-40b-instruct--configuration_falcon.FalconConfig",
    "AutoModelForCausalLM": "tiiuae/falcon-40b-instruct--modeling_falcon.FalconModel"
  },
  "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": "falcon",
  "new_decoder_architecture": true,
  "num_attention_heads": 128,
  "num_hidden_layers": 60,
  "num_kv_heads": 8,
  "parallel_attn": true,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "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": false,
    "load_in_8bit": true
  },
  "torch_dtype": "float16",
  "transformers_version": "4.30.0.dev0",
  "use_cache": true,
  "vocab_size": 65024
}