{
  "adaptor_config": {
    "alpha_pattern": {},
    "auto_mapping": null,
    "base_model_name_or_path": "",
    "bias": "none",
    "corda_config": null,
    "eva_config": null,
    "exclude_modules": null,
    "fan_in_fan_out": false,
    "inference_mode": true,
    "init_lora_weights": true,
    "layer_replication": null,
    "layers_pattern": null,
    "layers_to_transform": null,
    "loftq_config": {},
    "lora_alpha": 16,
    "lora_bias": false,
    "lora_dropout": 0.1,
    "megatron_config": null,
    "megatron_core": "megatron.core",
    "modules_to_save": null,
    "peft_type": "LORA",
    "qalora_group_size": 16,
    "r": 8,
    "rank_pattern": {},
    "revision": null,
    "target_modules": [
      "up_proj_k",
      "out_proj",
      "fc2",
      "up_proj_v",
      "q_proj",
      "dkv_proj",
      "fc1"
    ],
    "task_type": "CAUSAL_LM",
    "trainable_token_indices": null,
    "use_dora": false,
    "use_qalora": false,
    "use_rslora": false
  },
  "balance_loss_weight": 0.01,
  "bos_token_id": 2,
  "dropout": 0.1,
  "embed_dim": 640,
  "eos_token_id": 3,
  "experts_per_token": 2,
  "latent_dim": 160,
  "max_seq_len": 256,
  "mlp_dim": 1536,
  "model_type": "latent_moe_shim",
  "num_experts": 6,
  "num_heads": 8,
  "num_layers": 8,
  "pad_token_id": 0,
  "transformers_version": "4.53.2",
  "vocab_size": 30000
}