config.json

{
  "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,
  "rope_theta": 10000000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.56.1",
  "use_cache": true,
  "vocab_size": 155136,
  "quantization_config": {
    "quant_method": "gptq",
    "bits": 4,
    "desc_act": false,
    "group_size": 128,
    "hyb_act": false,
    "lm_head": false,
    "sym": true
  }
}