{
  "architectures": [
    "SeedOssForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.1,
  "attention_out_bias": false,
  "bos_token_id": 0,
  "dtype": "bfloat16",
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 524288,
  "mlp_bias": false,
  "model_type": "seed_oss",
  "num_attention_heads": 80,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "pad_token_id": 1,
  "pretraining_tp": 1,
  "quantization_config": {
    "autoround_version": "0.8.0.dev",
    "bits": 4,
    "damp_percent": 0.01,
    "data_type": "int",
    "desc_act": false,
    "group_size": 128,
    "provider": "auto-round",
    "quant_method": "gptq",
    "sym": true,
    "true_sequential": false
  },
  "residual_dropout": 0.1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "rope_type": "default"
  },
  "rope_theta": 10000000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.56.2",
  "use_cache": true,
  "vocab_size": 155136,
  "torch_dtype": "float16"
}