{
  "architectures": [
    "DeepseekV3ForCausalLM"
  ],
  "model_type": "deepseek_v3_mini",
  "hidden_size": 512,
  "intermediate_size": 1365,
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "n_routed_experts": 8,
  "num_experts_per_tok": 2,
  "latent_disturation_dim": 64,
  "vocab_size": 50257,
  "max_position_embeddings": 256,
  "rms_norm_eps": 1e-06,
  "torch_dtype": "float32"
}