models/Bidirectional-Parallel-Refresh/config.json

{
  "architectures": [
    "DMTDQwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_dmtdqwen3.DMTDQwen3Config",
    "AutoModel": "modeling_dmtdqwen3.DMTDQwen3Model",
    "AutoModelForCausalLM": "modeling_dmtdqwen3.DMTDQwen3ForCausalLM"
  },
  "bos_token_id": null,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "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": 151660,
  "max_position_embeddings": 40960,
  "max_window_layers": 36,
  "dmtd_history_mode": "real",
  "dmtd_block_attention": "bidirectional",
  "model_type": "dmtdqwen3",
  "mtp_horizon": 4,
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_parallel_layers": 28,
  "num_sequential_layers": 8,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 1000000,
    "rope_type": "default"
  },
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "5.6.2",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}