config.json

{
  "add_classification_head": false,
  "architectures": [
    "HunYuanDenseV1ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_head_dim": 128,
  "bos_token_id": 1,
  "cla_share_factor": 2,
  "class_num": 0,
  "dense_list": [
    2048,
    0
  ],
  "eod_token_id": 120026,
  "eos_token_id": 120020,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "im_end_id": 5,
  "im_newline_id": 11,
  "im_start_id": 4,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "mask_init_id": 12,
  "max_position_embeddings": 262144,
  "mlp_bias": false,
  "model_type": "hunyuan_v1_dense",
  "norm_type": "rms",
  "num_attention_heads": 16,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "org_vocab_size": 120818,
  "pad_id": 120002,
  "pad_token_id": 120002,
  "pool_type": "last",
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "alpha": 1000.0,
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 1.0,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "type": "dynamic"
  },
  "rope_theta": 10000.0,
  "sep_token_id": 120007,
  "text_end_id": 7,
  "text_start_id": 6,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_cla": false,
  "use_qk_norm": true,
  "use_rotary_pos_emb": true,
  "vocab_size": 120818
}