config.json

{
  "add_classification_head": false,
  "architectures": [
    "HunYuanDenseV1ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_head_dim": 128,
  "bos_token_id": 120000,
  "cla_share_factor": 2,
  "class_num": 0,
  "dense_list": [
    2048,
    0
  ],
  "dtype": "float32",
  "eos_token_id": 120020,
  "head_dim": 16,
  "hidden_act": "silu",
  "hidden_size": 64,
  "im_end_id": 5,
  "im_newline_id": 11,
  "im_start_id": 4,
  "initializer_range": 0.02,
  "intermediate_size": 128,
  "mask_init_id": 12,
  "max_position_embeddings": 262144,
  "mlp_bias": false,
  "model_type": "hunyuan_v1_dense",
  "norm_type": "rms",
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 2,
  "org_vocab_size": 120818,
  "pad_id": 120002,
  "pad_token_id": 120002,
  "pool_type": "last",
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "alpha": 1000.0,
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 1.0,
    "rope_theta": 10000.0,
    "rope_type": "dynamic",
    "type": "dynamic"
  },
  "sep_token_id": 120007,
  "text_end_id": 7,
  "text_start_id": 6,
  "tie_word_embeddings": true,
  "transformers_version": "5.0.0.dev0",
  "use_cache": true,
  "use_cla": false,
  "use_qk_norm": true,
  "use_rotary_pos_emb": true,
  "vocab_size": 120818,
  "transformers.js_config": {
    "use_external_data_format": {
      "model.onnx": 1,
      "model_fp16.onnx": 1
    },
    "kv_cache_dtype": {
      "q4f16": "float16",
      "fp16": "float16"
    }
  }
}