{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/tmp/models/tmpufm4jwo6/tmp81_2prvm",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "FalconForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_falcon.FalconConfig",
    "AutoModel": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconModel",
    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForCausalLM",
    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForQuestionAnswering",
    "AutoModelForSequenceClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForSequenceClassification",
    "AutoModelForTokenClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForTokenClassification"
  },
  "bias": false,
  "bos_token_id": 11,
  "eos_token_id": 11,
  "hidden_dropout": 0.0,
  "hidden_size": 4544,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "falcon",
  "multi_query": true,
  "new_decoder_architecture": false,
  "num_attention_heads": 71,
  "num_hidden_layers": 32,
  "num_kv_heads": 71,
  "parallel_attn": true,
  "quantization_config": {
    "quant_config": {
      "offload_meta": false,
      "scale_quant_params": null,
      "weight_quant_params": {
        "axis": 1,
        "channel_wise": true,
        "group_size": 64,
        "nbits": 8,
        "optimize": true,
        "round_zero": false,
        "view_as_float": false
      },
      "zero_quant_params": null
    },
    "quant_method": "hqq",
    "skip_modules": [
      "lm_head"
    ]
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.2",
  "use_cache": true,
  "vocab_size": 65024
}