{
  "_name_or_path": "/data6/models/DeepSeek-V2.5-1210",
  "architectures": [
    "DeepseekV2ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV2Config",
    "AutoModel": "modeling_deepseek.DeepseekV2Model",
    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
  },
  "aux_loss_alpha": 0.001,
  "bos_token_id": 100000,
  "eos_token_id": 100001,
  "ep_size": 1,
  "first_k_dense_replace": 1,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "kv_lora_rank": 512,
  "max_position_embeddings": 163840,
  "model_type": "deepseek_v2",
  "moe_intermediate_size": 1536,
  "moe_layer_freq": 1,
  "n_group": 8,
  "n_routed_experts": 160,
  "n_shared_experts": 2,
  "norm_topk_prob": false,
  "num_attention_heads": 128,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 60,
  "num_key_value_heads": 128,
  "pretraining_tp": 1,
  "q_lora_rank": 1536,
  "qk_nope_head_dim": 128,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.4.3",
    "batch_size": 2,
    "bits": 4,
    "damp_percent": 0.01,
    "data_type": "int",
    "desc_act": false,
    "enable_minmax_tuning": true,
    "enable_norm_bias_tuning": false,
    "enable_quanted_input": true,
    "gradient_accumulate_steps": 4,
    "group_size": 128,
    "iters": 200,
    "low_gpu_mem_usage": true,
    "lr": 0.005,
    "minmax_lr": 0.005,
    "nsamples": 128,
    "quant_method": "gptq",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true,
    "to_quant_block_names": null,
    "true_sequential": false
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 40,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 4096,
    "type": "yarn"
  },
  "rope_theta": 10000,
  "routed_scaling_factor": 16.0,
  "scoring_func": "softmax",
  "seq_aux": true,
  "tie_word_embeddings": false,
  "topk_group": 3,
  "topk_method": "group_limited_greedy",
  "torch_dtype": "float16",
  "transformers_version": "4.47.0",
  "use_cache": true,
  "v_head_dim": 128,
  "vocab_size": 102400
}