{
  "_name_or_path": "/data/huggingface_cache/hub/models--tiiuae--falcon-40b/snapshots/4a70170c215b36a3cce4b4253f6d0612bb7d4146",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "FalconForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_falcon.FalconConfig",
    "AutoModel": "modeling_falcon.FalconModel",
    "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
    "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
    "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
  },
  "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,
  "max_position_embeddings": 2048,
  "model_type": "falcon",
  "multi_query": true,
  "new_decoder_architecture": true,
  "num_attention_heads": 128,
  "num_hidden_layers": 60,
  "num_kv_heads": 8,
  "parallel_attn": true,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "modules_to_not_convert": null,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "torch_dtype": "float16",
  "transformers_version": "4.38.1",
  "use_cache": false,
  "vocab_size": 65024
}