config.json

{
  "architectures": [
    "WeDLMForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_wedlm.WeDLMConfig",
    "AutoModel": "modeling_wedlm.WeDLMForCausalLM",
    "AutoModelForCausalLM": "modeling_wedlm.WeDLMForCausalLM"
  },
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "flow_block_size": 64,
  "flow_discretization": "argmax",
  "flow_inference_steps": 8,
  "flow_init_sigma": 1.0,
  "flow_loss_weight": 1.0,
  "flow_temperature": 1.0,
  "flow_time_embedding_dim": 256,
  "flow_time_embedding_max_period": 10000,
  "flow_time_scale": 1000.0,
  "flow_top_k": 0,
  "flow_top_p": 1.0,
  "flow_train_block_size": 64,
  "flow_train_mask_ratio": 0.15,
  "flow_train_min_target_tokens": 1,
  "flow_train_strategy": "suffix_block",
  "flow_type": "rectified_flow",
  "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",
    "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": 48,
  "model_type": "wedlm",
  "num_attention_heads": 32,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "pad_token_id": 151643,
  "qk_norm": 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": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}