config.json

{
  "_name_or_path": "/models/falcon-7b",
  "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": 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": {
    "autoround_version": "0.2.0.dev",
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": false,
    "enable_minmax_tuning": true,
    "enable_quanted_input": false,
    "group_size": 64,
    "is_marlin_format": false,
    "iters": 1000,
    "lr": 0.001,
    "minmax_lr": 0.001,
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "scale_dtype": "float16",
    "static_groups": false,
    "sym": false,
    "true_sequential": false
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.2",
  "use_cache": true,
  "vocab_size": 65024
}