{
  "_name_or_path": "/workspace/falcon-180b-chat-gptq-main",
  "alibi": false,
  "architectures": [
    "FalconForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bias": false,
  "bos_token_id": 11,
  "eos_token_id": 11,
  "hidden_dropout": 0.0,
  "hidden_size": 14848,
  "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": 232,
  "num_hidden_layers": 80,
  "num_kv_heads": 8,
  "pad_token_id": 0,
  "parallel_attn": true,
  "pretraining_tp": 1,
  "quantization_config": {
    "batch_size": 1,
    "bits": 4,
    "block_name_to_quantize": null,
    "damp_percent": 0.1,
    "dataset": null,
    "desc_act": true,
    "disable_exllama": true,
    "group_size": -1,
    "model_seqlen": null,
    "module_name_preceding_first_block": null,
    "pad_token_id": null,
    "quant_method": "gptq",
    "sym": true,
    "tokenizer": null,
    "true_sequential": true,
    "use_cuda_fp16": false
  },
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "torch_dtype": "float16",
  "transformers_version": "4.33.0",
  "use_cache": true,
  "vocab_size": 65024
}