config.json

{
  "architectures": [
    "Exaone4ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "dtype": "bfloat16",
  "eos_token_id": 361,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 65536,
  "model_type": "exaone4",
  "num_attention_heads": 32,
  "num_hidden_layers": 30,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "int-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "token",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        }
      }
    },
    "format": "int-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": {
      "actorder": null,
      "block_structure": null,
      "dynamic": false,
      "group_size": null,
      "num_bits": 4,
      "observer": "minmax",
      "observer_kwargs": {},
      "scale_dtype": null,
      "strategy": "tensor",
      "symmetric": true,
      "type": "int",
      "zp_dtype": null
    },
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.13.0"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 16.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "sliding_window_pattern": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 102400
}