config.json

{
  "architectures": [
    "DeepseekForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_bailing.DeepseekConfig",
    "AutoModel": "modeling_bailing.DeepseekModel",
    "AutoModelForCausalLM": "modeling_bailing.DeepseekForCausalLM"
  },
  "aux_loss_alpha": 0.001,
  "bos_token_id": 50000,
  "compression_config": {
    "config_groups": {
      "group_0": {
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "channel",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": 1.5898760470082427,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed"
  },
  "eos_token_id": 50000,
  "first_k_dense_replace": 0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.006,
  "intermediate_size": 5632,
  "max_position_embeddings": 4096,
  "model_type": "deepseek",
  "moe_intermediate_size": 1408,
  "moe_layer_freq": 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": 28,
  "num_key_value_heads": 4,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000,
  "scoring_func": "softmax",
  "seq_aux": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.46.0",
  "use_cache": true,
  "vocab_size": 126464
}