{
  "_remove_final_layer_norm": false,
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "OPTForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "do_layer_norm_before": true,
  "dropout": 0.1,
  "enable_bias": true,
  "eos_token_id": 2,
  "ffn_dim": 3072,
  "hidden_size": 768,
  "init_std": 0.02,
  "layer_norm_elementwise_affine": true,
  "layerdrop": 0.0,
  "max_position_embeddings": 2048,
  "model_type": "opt",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "prefix": "</s>",
  "quantization_config": {
    "include_input_output_embeddings": false,
    "modules_to_not_convert": null,
    "quant_method": "torchao",
    "quant_type": {
      "default": {
        "_data": {
          "group_size": 128,
          "int4_choose_qparams_algorithm": {
            "_data": "TINYGEMM",
            "_type": "Int4ChooseQParamsAlgorithm"
          },
          "int4_packing_format": {
            "_data": "PLAIN",
            "_type": "Int4PackingFormat"
          },
          "layout": {
            "_data": {
              "inner_k_tiles": 8
            },
            "_type": "TensorCoreTiledLayout",
            "_version": 1
          },
          "preserve_zero": null,
          "set_inductor_config": true,
          "use_hqq": false,
          "zero_point_domain": {
            "_data": "NONE",
            "_type": "ZeroPointDomain"
          }
        },
        "_type": "Int4WeightOnlyConfig",
        "_version": 1
      }
    },
    "quant_type_kwargs": {},
    "untie_embedding_weights": false
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 50272,
  "word_embed_proj_dim": 768
}