Unable to Merge LoRA Weights with Base Model: ValueError: Can't find 'adapter_config.json' at ...

[PARSA-MHMDI]

I’m encountering an issue while trying to merge LoRA weights with a base model after fine-tuning the gemma-2B model. In the output folder, I see three files:

• mm_projector.bin

• trainer_state.json

• config.json

The problem arises when I attempt to merge the LoRA weights with the base model. I consistently receive the following error. I am using this command: !python /content/MGM/scripts/merge_lora_weights.py --model-base /content/MGM/work_dirs/MGM/MGM-2B --model-path /content/MGM/work_dirs/Parsa --save-model-path /content/MGM/work_dirs/Parsa/merged

But I got this error:

/usr/local/lib/python3.10/dist-packages/transformers/deepspeed.py:24: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
  warnings.warn(
[2024-09-05 20:59:18,475] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
 [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
 [WARNING]  async_io: please install the libaio-dev package with apt
 [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
/usr/local/lib/python3.10/dist-packages/deepspeed/runtime/zero/linear.py:49: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  def forward(ctx, input, weight, bias=None):
/usr/local/lib/python3.10/dist-packages/deepspeed/runtime/zero/linear.py:67: FutureWarning: `torch.cuda.amp.custom_bwd(args...)` is deprecated. Please use `torch.amp.custom_bwd(args..., device_type='cuda')` instead.
  def backward(ctx, grad_output):
2024-09-05 20:59:20.849993: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-09-05 20:59:20.867369: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-09-05 20:59:20.888264: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-09-05 20:59:20.894552: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-09-05 20:59:20.909843: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-09-05 20:59:22.040155: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
`config.hidden_act` is ignored, you should use `config.hidden_activation` instead.
Gemma's activation function will be set to `gelu_pytorch_tanh`. Please, use
`config.hidden_activation` if you want to override this behaviour.
See https://github.com/huggingface/transformers/pull/29402 for more details.
Loading checkpoint shards: 100% 2/2 [00:01<00:00,  1.07it/s]
Loading LoRA weights from /content/MGM/work_dirs/Parsa
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/peft/config.py", line 205, in _get_peft_type
    config_file = hf_hub_download(
  File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py", line 101, in inner_f
    return f(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
    validate_repo_id(arg_value)
  File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
    raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/content/MGM/work_dirs/Parsa'. Use `repo_type` argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/content/MGM/scripts/merge_lora_weights.py", line 22, in <module>
    merge_lora(args)
  File "/content/MGM/scripts/merge_lora_weights.py", line 8, in merge_lora
    tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, device_map='cpu')
  File "/content/MGM/mgm/model/builder.py", line 86, in load_pretrained_model
    model = PeftModel.from_pretrained(model, model_path)
  File "/usr/local/lib/python3.10/dist-packages/peft/peft_model.py", line 453, in from_pretrained
    PeftConfig._get_peft_type(
  File "/usr/local/lib/python3.10/dist-packages/peft/config.py", line 211, in _get_peft_type
    raise ValueError(f"Can't find '{CONFIG_NAME}' at '{model_id}'")
ValueError: Can't find 'adapter_config.json' at '/content/MGM/work_dirs/Parsa'

Has anyone faced this issue or can offer some guidance on resolving it?

Thank you!