from transformers import AutoModelForSequenceClassification, AutoTokenizer
# Define the path to the checkpoint
checkpoint_path = r"./results/checkpoint-1000" # Replace with your checkpoint folder
# Load the model
model = AutoModelForSequenceClassification.from_pretrained("Training/AI/GenAI/ai-innovation-bridge/workshops/ai-workloads-with-huggingface/results/checkpoint-1000")
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
from transformers import cached_file
# Replace with the actual values
path_or_repo_id = "username/repository"
filename = "model_file.bin"
cache_dir = "path/to/cache_dir"
# Download the file
resolved_file = cached_file(
path_or_repo_id=path_or_repo_id,
filename=filename,
cache_dir=cache_dir,
force_download=True, # Set to True to force download
resume_download=True, # Set to True to resume download if it was interrupted
proxies=None, # Set to your proxy settings if needed
token=None, # Set to your Hugging Face token if the repository is gated
revision=None, # Set to a specific commit hash or tag if needed
local_files_only=True, # Set to True to only look for local files
subfolder=None, # Set to a subfolder if the file is in a subfolder
repo_type=None, # Set to "dataset" or "model" if necessary
user_agent=None, # Set to a custom user agent if needed
_raise_exceptions_for_gated_repo=True, # Set to False to not raise exceptions for gated repositories
_raise_exceptions_for_missing_entries=True, # Set to False to not raise exceptions for missing entries
_raise_exceptions_for_connection_errors=True, # Set to False to not raise exceptions for connection errors
_commit_hash=None, # Set to a specific commit hash if needed
)
# Use the resolved_file path for further processing
This code produces the following error and I am stuck with this for quite some time now. Please suggest a quick fix to proceed.
File ~/.local/lib/python3.11/site-packages/transformers/utils/hub.py:385, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)
383 try:
384 # Load from URL or cache if already cached
--> 385 resolved_file = hf_hub_download(
386 path_or_repo_id,
387 filename,
388 subfolder=None if len(subfolder) == 0 else subfolder,
389 repo_type=repo_type,
390 revision=revision,
391 cache_dir=cache_dir,
392 user_agent=user_agent,
393 force_download=force_download,
394 proxies=proxies,
395 resume_download=resume_download,
396 token=token,
397 local_files_only=local_files_only,
398 )
399 except GatedRepoError as e:
File ~/.local/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py:110, in validate_hf_hub_args.<locals>._inner_fn(*args, **kwargs)
109 if arg_name in ["repo_id", "from_id", "to_id"]:
--> 110 validate_repo_id(arg_value)
112 elif arg_name == "token" and arg_value is not None:
File ~/.local/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py:158, in validate_repo_id(repo_id)
157 if repo_id.count("/") > 1:
--> 158 raise HFValidationError(
159 "Repo id must be in the form 'repo_name' or 'namespace/repo_name':"
160 f" '{repo_id}'. Use `repo_type` argument if needed."
161 )
163 if not REPO_ID_REGEX.match(repo_id):
HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'Training/AI/GenAI/ai-innovation-bridge/workshops/ai-workloads-with-huggingface/results/checkpoint-1000'. Use `repo_type` argument if needed.
The above exception was the direct cause of the following exception:
OSError Traceback (most recent call last)
Cell In[3], line 7
4 checkpoint_path = r"./results/checkpoint-1000" # Replace with your checkpoint folder
6 # Load the model
----> 7 model = AutoModelForSequenceClassification.from_pretrained("Training/AI/GenAI/ai-innovation-bridge/workshops/ai-workloads-with-huggingface/results/checkpoint-1000")
9 # Load the tokenizer
10 tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
File ~/.local/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py:488, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
485 if commit_hash is None:
486 if not isinstance(config, PretrainedConfig):
487 # We make a call to the config file first (which may be absent) to get the commit hash as soon as possible
--> 488 resolved_config_file = cached_file(
489 pretrained_model_name_or_path,
490 CONFIG_NAME,
491 _raise_exceptions_for_missing_entries=False,
492 _raise_exceptions_for_connection_errors=False,
493 **hub_kwargs,
494 )
495 commit_hash = extract_commit_hash(resolved_config_file, commit_hash)
496 else:
File ~/.local/lib/python3.11/site-packages/transformers/utils/hub.py:450, in cached_file(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)
448 raise EnvironmentError(f"There was a specific connection error when trying to load {path_or_repo_id}:\n{err}")
449 except HFValidationError as e:
--> 450 raise EnvironmentError(
451 f"Incorrect path_or_model_id: '{path_or_repo_id}'. Please provide either the path to a local folder or the repo_id of a model on the Hub."
452 ) from e
453 return resolved_file
OSError: Incorrect path_or_model_id: 'Training/AI/GenAI/ai-innovation-bridge/workshops/ai-workloads-with-huggingface/results/checkpoint-1000'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
