You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Looks like base model Vicuna v1.5 is not downloaded automatically when I run the provided training scripts. Did anyone face this issue?
Traceback (most recent call last):
File "/miniconda/envs/llava/lib/python3.10/site-packages/transformers/utils/hub.py", line 385, in cached_file
resolved_file = hf_hub_download(
File "/miniconda/envs/llava/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 111, in _inner_fn
validate_repo_id(arg_value)
File "/miniconda/envs/llava/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 159, in validate_repo_id
raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './checkpoints/vicuna-7b-v1-5'. Use `repo_type` argument if needed.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/LLaVA/llava/train/train_mem.py", line 4, in <module>
train(attn_implementation="flash_attention_2")
File "/LLaVA/llava/train/train.py", line 827, in train
model = LlavaLlamaForCausalLM.from_pretrained(
File "/miniconda/envs/llava/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3075, in from_pretrained
config, model_kwargs = cls.config_class.from_pretrained(
File "/miniconda/envs/llava/lib/python3.10/site-packages/transformers/configuration_utils.py", line 605, in from_pretrained
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/miniconda/envs/llava/lib/python3.10/site-packages/transformers/configuration_utils.py", line 634, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/miniconda/envs/llava/lib/python3.10/site-packages/transformers/configuration_utils.py", line 689, in _get_config_dict
resolved_config_file = cached_file(
File "/miniconda/envs/llava/lib/python3.10/site-packages/transformers/utils/hub.py", line 450, in cached_file
raise EnvironmentError(
OSError: Incorrect path_or_model_id: './checkpoints/vicuna-7b-v1-5'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
The text was updated successfully, but these errors were encountered:
I have exactly the same error, it took me a while to find it.
Ensure the script you are calling is bash scripts/v1_5/pretrain.sh NOT bash scripts/pretrain.sh and in the file --model_name_or_path lmsys/vicuna-13b-v1.5
Describe the issue
Looks like base model Vicuna v1.5 is not downloaded automatically when I run the provided training scripts. Did anyone face this issue?
The text was updated successfully, but these errors were encountered: