NVILA Fine Tuning Process Not clear

[rahuljoshi078]

Following repo cloned:
git clone https://huggingface.co/Efficient-Large-Model/NVILA-15B

We have used a custom dataset and preprocessed it to create a .pkl file which will be used for fine-tuning. Post that we executed the following bash command i.e.
bash scripts/NVILA/stage3_9tile.sh runs/train/NVILA-15B /home/sample_ft/M3IT/data/captioning/coco/captioning_coco_train.pkl

Error:
[rank0]: Traceback (most recent call last):
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/transformers/utils/hub.py", line 403, in cached_file
[rank0]: resolved_file = hf_hub_download(
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
[rank0]: validate_repo_id(arg_value)
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
[rank0]: raise HFValidationError(
[rank0]: huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'runs/train/stage2_9tile/model'. Use repo_type argument if needed.

[rank0]: The above exception was the direct cause of the following exception:

[rank0]: Traceback (most recent call last):
[rank0]: File "/home/user/VILA/llava/train/train_mem.py", line 49, in
[rank0]: train()
[rank0]: File "/home/user/VILA/llava/train/train.py", line 497, in train
[rank0]: config = LlavaLlamaConfig.from_pretrained(model_args.model_name_or_path, resume=resume_from_checkpoint)
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/transformers/configuration_utils.py", line 545, in from_pretrained
[rank0]: config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/transformers/configuration_utils.py", line 574, in get_config_dict
[rank0]: config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/transformers/configuration_utils.py", line 633, in _get_config_dict
[rank0]: resolved_config_file = cached_file(
[rank0]: File "/root/anaconda3/envs/vila_adv/lib/python3.10/site-packages/transformers/utils/hub.py", line 469, in cached_file
[rank0]: raise EnvironmentError(
[rank0]: OSError: Incorrect path_or_model_id: 'runs/train/stage2_9tile/model'. Please provide either the path to a local folder or the repo_id of a model on the Hub.

It is given in the documentation that one need to use sft.sh file for Supervised Fine Tuning in case of NVILA-8B. The similar process we have followed for NVILA-15B model i.e. scripts/NVILA/stage3_9tile.sh
The above mentioned bash command required Data Mixtures argument which is passed as an empty string in stage3_9tiles.sh file. Also there is some model path mismatch we are facing.

Is this regarding some git repo issue? Kindly do suggest some solution.