config.json

{
  "architectures": [
    "WeDLMForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_wedlm.WeDLMConfig",
    "AutoModelForCausalLM": "modeling_wedlm.WeDLMForCausalLM"
  },
  "dtype": "bfloat16",
  "eos_token_id": 151643,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "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",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "mask_token_id": null,
  "max_position_embeddings": 16384,
  "max_window_layers": 36,
  "model_type": "wedlm",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "pad_token_id": 151643,
  "qk_norm": true,
  "quantization_config": {
    "autoround_version": "0.9.5",
    "bits": 4,
    "data_type": "int",
    "group_size": 128,
    "packing_format": "auto_round:auto_gptq",
    "quant_method": "auto-round",
    "sym": true
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}