config.json

{
  "architectures": [
    "DeepseekV3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
    "AutoModel": "modeling_deepseek.DeepseekV3Model",
    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
  },
  "aux_loss_alpha": 0.001,
  "bos_token_id": 163584,
  "eos_token_id": 163585,
  "ep_size": 1,
  "first_k_dense_replace": 1,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 11264,
  "kv_lora_rank": 512,
  "max_position_embeddings": 8192,
  "model_type": "deepseek_v3",
  "moe_intermediate_size": 1408,
  "moe_layer_freq": 1,
  "n_group": 1,
  "n_routed_experts": 64,
  "n_shared_experts": 2,
  "norm_topk_prob": true,
  "num_attention_heads": 16,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 27,
  "num_key_value_heads": 16,
  "num_nextn_predict_layers": 0,
  "pretraining_tp": 1,
  "q_lora_rank": null,
  "qk_nope_head_dim": 128,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "bits": 2,
    "checkpoint_format": "gptq",
    "desc_act": true,
    "group_size": -1,
    "lm_head": false,
    "meta": {
      "damp_auto_increment": 0.0025,
      "damp_percent": 0.01,
      "mse": 0.0,
      "quantizer": [
        "gptqmodel:3.0.0-dev"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "v2": false,
      "v2_alpha": 0.25
    },
    "pack_dtype": "int32",
    "quant_method": "gptq",
    "sym": true
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 50000.0,
  "routed_scaling_factor": 2.446,
  "scoring_func": "sigmoid",
  "seq_aux": true,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "topk_method": "noaux_tc",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "v_head_dim": 128,
  "vocab_size": 163840
}