adapter_config.json

{
  "auto_mapping": {
    "base_model_class": "TensorParallelPreTrainedModel",
    "parent_library": "tensor_parallel.pretrained_model"
  },
  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
  "bias": "none",
  "fan_in_fan_out": false,
  "inference_mode": true,
  "init_lora_weights": true,
  "layers_pattern": null,
  "layers_to_transform": null,
  "lora_alpha": 32,
  "lora_dropout": 0.05,
  "modules_to_save": null,
  "peft_type": "LORA",
  "r": 16,
  "revision": null,
  "target_modules": [
    "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.q_proj",
    "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.k_proj",
    "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.v_proj",
    "wrapped_model.module_shards.0.model.layers.31.self_attn.tp_wrapped_module.o_proj",
    "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.gate_proj",
    "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.up_proj",
    "wrapped_model.module_shards.0.model.layers.31.mlp.tp_wrapped_module.down_proj",
    "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.q_proj",
    "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.k_proj",
    "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.v_proj",
    "wrapped_model.module_shards.1.model.layers.31.self_attn.tp_wrapped_module.o_proj",
    "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.gate_proj",
    "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.up_proj",
    "wrapped_model.module_shards.1.model.layers.31.mlp.tp_wrapped_module.down_proj"
  ],
  "task_type": null
}