config.json

{
  "architectures": ["DeepseekV4ForCausalLM"],
  "model_type": "deepseek_v4",
  "model_id": "sovereign/deepseek-v4-sovereign",
  "base_model": "deepseek-ai/DeepSeek-V4-Flash-0731",
  "torch_dtype": "bfloat16",
  "vocab_size": 129280,
  "hidden_size": 7168,
  "num_hidden_layers": 61,
  "num_attention_heads": 64,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "num_experts": 256,
  "num_experts_per_tok": 8,
  "intermediate_size": 18432,
  "max_position_embeddings": 1048576,
  "rope_theta": 1000000.0,
  "speculative_decoding": {
    "method": "dspark",
    "num_speculative_tokens": 7,
    "draft_sample_method": "greedy"
  },
  "moe": {
    "backend": "deep_gemm_mega_moe",
    "expert_parallel": true
  },
  "attention": {
    "use_fp4_indexer_cache": true,
    "swa_full_tokens_ratio": 0.1
  },
  "quantization_config": {
    "quant_method": "gptq",
    "bits": 4,
    "group_size": 128,
    "damp_percent": 0.01
  },
  "transformers_version": "4.46.0"
}