g d dl Z d dlZd dlmZ d dlmZmZmZmZm Z m
Z
d dl Z d dl Z d dl
mZ d dlmZ d dlmZmZmZmZmZmZmZ d dlmZmZm Z dd l m Z dd
l m Z dd l!m"Z"m#Z#m$Z$ e#jJ e& Z' ee( jR d z d
z Z* ee( jR d z dz Z+ ejX d Z- G d d Z. G d de. Z/ G d de. Z0 G d de. Z1de2ded fdZ3d e
e2ef dee fd Z4d e
e2ef d eddfd Z5dd ddddd!d"e2d#e2d$e2d%e2d&e2d'ed(e2d)e2d*ee2 d+e6d,ee2 d-ee2 d.ee2 d/ee2 def d0Z7e$dd ddddd dd1d2e2d3ed4ee2 d5e6d6ee2 d7ee2 d8ee2 d9ee2 d:e6d;ee2 de2fd< Z8y)= N)Path)AnyDictLiteralOptionalTypeUnion)hf_hub_download) upload_file)CardDataDatasetCardData
EvalResult
ModelCardData
SpaceCardDataeval_results_to_model_indexmodel_index_to_eval_results) get_sessionis_jinja_available yaml_dump ) constants)EntryNotFoundError)SoftTemporaryDirectoryloggingvalidate_hf_hub_args templateszmodelcard_template.mdzdatasetcard_template.mdz1^(\s*---[\r\n]+)([\S\s]*?)([\r\n]+---(\r\n|\n|$))c f e Zd ZeZeZdZddede fdZ
e d Z e j defd Z d Zdeeef fd Ze d d eeef d ee d
ee de fd Zd d ee fdZ d ded
ee d ee dee dee dee dee dee fdZe d dedee dee fd Zy
) RepoCardmodelcontentignore_metadata_errorsc || _ || _ y)a Initialize a RepoCard from string content. The content should be a
Markdown file with a YAML block at the beginning and a Markdown body.
Args:
content (`str`): The content of the Markdown file.
Example:
```python
>>> from huggingface_hub.repocard import RepoCard
>>> text = '''
... ---
... language: en
... license: mit
... ---
...
... # My repo
... '''
>>> card = RepoCard(text)
>>> card.data.to_dict()
{'language': 'en', 'license': 'mit'}
>>> card.text
'\n# My repo\n'
```
Raises the following error:
- [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
when the content of the repo card metadata is not a dictionary.
N)r! r )selfr r! s M/var/www/openai/venv/lib/python3.12/site-packages/huggingface_hub/repocard.py__init__zRepoCard.__init__+ s H '=# c t | j xs d}d| | j j || j | d| | j
S )zLThe content of the RepoCard, including the YAML block and the Markdown body.
---)
line_breakoriginal_order)_detect_line_ending_contentdatato_yaml_original_ordertext)r# r* s r$ r zRepoCard.contentR s} ) 7?4
ZL!2!2jY]YmYm!2!n opzo{{~ @J K LP LU LU KV W Wr& c || _ t j | }|r]|j d }||j d | _ t
j | }|i }t |t s)t d t j d i }|| _ | j di |d| j i| _ t! |j# | _ y)z Set the content of the RepoCard. N)repo card metadata block should be a dictzBRepo card metadata block was not found. Setting CardData to empty.r! )r- REGEX_YAML_BLOCKsearchgroupendr1 yaml safe_load
isinstancedict
ValueErrorloggerwarningcard_data_classr! r. listkeysr0 )r# r match
yaml_block data_dicts r$ r zRepoCard.contentX s
''0 Q J
.DI z2I i. !LMM
NN_ `I DI(D((i9iTMhMhi #INN$4 5 r& c | j S N)r )r# s r$ __str__zRepoCard.__str__s s ||r& filepathc t | }|j j dd t |ddd 5 }|j t | ddd y# 1 sw Y yxY w)a{ Save a RepoCard to a file.
Args:
filepath (`Union[Path, str]`): Filepath to the markdown file to save.
Example:
```python
>>> from huggingface_hub.repocard import RepoCard
>>> card = RepoCard("---\nlanguage: en\n---\n# This is a test repo card")
>>> card.save("/tmp/test.md")
```
T)parentsexist_okw utf-8modenewlineencodingN)r parentmkdiropenwritestr)r# rJ fs r$ savez
RepoCard.savev sQ > dT :
(b7
Cq
GGCI D
C
Cs A A%Nrepo_id_or_path repo_typetokenc x t | j r t | }nTt |t r5t t |t
j |xs | j | }nt d| d |j ddd 5 } | |j | cd d d S # 1 sw Y y xY w)
a Initialize a RepoCard from a Hugging Face Hub repo's README.md or a local filepath.
Args:
repo_id_or_path (`Union[str, Path]`):
The repo ID associated with a Hugging Face Hub repo or a local filepath.
repo_type (`str`, *optional*):
The type of Hugging Face repo to push to. Defaults to None, which will use use "model". Other options
are "dataset" and "space". Not used when loading from a local filepath. If this is called from a child
class, the default value will be the child class's `repo_type`.
token (`str`, *optional*):
Authentication token, obtained with `huggingface_hub.HfApi.login` method. Will default to the stored token.
ignore_metadata_errors (`str`):
If True, errors while parsing the metadata section will be ignored. Some information might be lost during
the process. Use it at your own risk.
Returns:
[`huggingface_hub.repocard.RepoCard`]: The RepoCard (or subclass) initialized from the repo's
README.md file or filepath.
Example:
```python
>>> from huggingface_hub.repocard import RepoCard
>>> card = RepoCard.load("nateraw/food")
>>> assert card.data.tags == ["generated_from_trainer", "image-classification", "pytorch"]
```
)r] r^ z.Cannot load RepoCard: path not found on disk (z).rrO rP rQ )r! N) r existsr< rY r
r
REPOCARD_NAMEr] r> rW read)clsr\ r] r^ r! card_pathrZ s r$ loadz
RepoCard.load s H ' ' ) _-I
- # ++ ' 83== I MoM^^` ab b ^^b7^
Cqqvvx8NO D
C
Cs B00B9c 8 |xs | j }|t | d}ddi} t j d|| }|j y# t
j j $ r+}j dk( rt |j |d}~ww xY w)a Validates card against Hugging Face Hub's card validation logic.
Using this function requires access to the internet, so it is only called
internally by [`huggingface_hub.repocard.RepoCard.push_to_hub`].
Args:
repo_type (`str`, *optional*, defaults to "model"):
The type of Hugging Face repo to push to. Options are "model", "dataset", and "space".
If this function is called from a child class, the default will be the child class's `repo_type`.
Raises the following errors:
- [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError)
if the card fails validation checks.
- [`HTTPError`](https://requests.readthedocs.io/en/latest/api/#requests.HTTPError)
if the request to the Hub API fails for any other reason.
)repoTyper Acceptz
text/plainz(https://huggingface.co/api/validate-yaml)headersi N) r] rY r postraise_for_statusrequests
exceptions HTTPError status_coder> r1 )r# r] bodyrj r` excs r$ validatezRepoCard.validate s , / "4y
\*
""#Mt]d"eA
"",, }}# (( s ,A B.&BBrepo_idcommit_messagecommit_descriptionrevision create_pr
parent_commitc
N |xs | j }| j | t 5 } t | t j
z }
|
j
t | t t |
t j
||||||||
} ddd | S # 1 sw Y S xY w)aA Push a RepoCard to a Hugging Face Hub repo.
Args:
repo_id (`str`):
The repo ID of the Hugging Face Hub repo to push to. Example: "nateraw/food".
token (`str`, *optional*):
Authentication token, obtained with `huggingface_hub.HfApi.login` method. Will default to
the stored token.
repo_type (`str`, *optional*, defaults to "model"):
The type of Hugging Face repo to push to. Options are "model", "dataset", and "space". If this
function is called by a child class, it will default to the child class's `repo_type`.
commit_message (`str`, *optional*):
The summary / title / first line of the generated commit.
commit_description (`str`, *optional*)
The description of the generated commit.
revision (`str`, *optional*):
The git revision to commit from. Defaults to the head of the `"main"` branch.
create_pr (`bool`, *optional*):
Whether or not to create a Pull Request with this commit. Defaults to `False`.
parent_commit (`str`, *optional*):
The OID / SHA of the parent commit, as a hexadecimal string. Shorthands (7 first characters) are also supported.
If specified and `create_pr` is `False`, the commit will fail if `revision` does not point to `parent_commit`.
If specified and `create_pr` is `True`, the pull request will be created from `parent_commit`.
Specifying `parent_commit` ensures the repo has not changed before committing the changes, and can be
especially useful if the repo is updated / committed to concurrently.
Returns:
`str`: URL of the commit which updated the card metadata.
)r] )
path_or_fileobj path_in_report r^ r] ru rv rx rw ry N) r] rs r r r rb
write_textrY r ) r# rt r^ r] ru rv rw rx ry tmpdirtmp_pathurls r$ push_to_hubzRepoCard.push_to_hub s R /
*
#
%F|i&=&==H D * #H
& 4 4 # -#5#! + C &
&
s A#BB$ card_data
template_path template_strc t rddl}n t d |j j }|j | |t
| j }|#t
| j j }|j | } |j dd|j i|} | | S )a' Initialize a RepoCard from a template. By default, it uses the default template.
Templates are Jinja2 templates that can be customized by passing keyword arguments.
Args:
card_data (`huggingface_hub.CardData`):
A huggingface_hub.CardData instance containing the metadata you want to include in the YAML
header of the repo card on the Hugging Face Hub.
template_path (`str`, *optional*):
A path to a markdown file with optional Jinja template variables that can be filled
in with `template_kwargs`. Defaults to the default template.
Returns:
[`huggingface_hub.repocard.RepoCard`]: A RepoCard instance with the specified card data and content from the
template.
r NzjUsing RepoCard.from_template requires Jinja2 to be installed. Please install it with `pip install Jinja2`.r r5 ) r jinja2 ImportErrorto_dictcopyupdater read_textdefault_template_pathTemplaterenderr/ ) rd r r r template_kwargsr kwargstemplater s r$
from_templatezRepoCard.from_template& s 0 9
""$))+
o& $
.88:L 9 9:DDFL??<0!(//JI,=,=,?J6J7|r& )F)NNFrH )NNNNNNNNN)__name__
__module__ __qualname__r rA TEMPLATE_MODELCARD_PATHr r] rY boolr% propertyr setterrI r r r[ classmethodr rf rs r r r5 r& r$ r r & s O 3I% % T % N W W
^^6s 6 64 U49 - ( $( #', 3P sDy)3P C=3P } 3P
!% 3P 3Pj%(3- %T $#'(,,0"&$('+== }= C= =
!
= %SM
= 3-= D>= }=~ (,&* ( ( }( sm ( ( r& r c T e Zd ZeZeZdZe ddede e
de e
f fd
Z xZ S ) ModelCardr r r r c ( t | |||fi |S )a
Initialize a ModelCard from a template. By default, it uses the default template, which can be found here:
https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md
Templates are Jinja2 templates that can be customized by passing keyword arguments.
Args:
card_data (`huggingface_hub.ModelCardData`):
A huggingface_hub.ModelCardData instance containing the metadata you want to include in the YAML
header of the model card on the Hugging Face Hub.
template_path (`str`, *optional*):
A path to a markdown file with optional Jinja template variables that can be filled
in with `template_kwargs`. Defaults to the default template.
Returns:
[`huggingface_hub.ModelCard`]: A ModelCard instance with the specified card data and content from the
template.
Example:
```python
>>> from huggingface_hub import ModelCard, ModelCardData, EvalResult
>>> # Using the Default Template
>>> card_data = ModelCardData(
... language='en',
... license='mit',
... library_name='timm',
... tags=['image-classification', 'resnet'],
... datasets=['beans'],
... metrics=['accuracy'],
... )
>>> card = ModelCard.from_template(
... card_data,
... model_description='This model does x + y...'
... )
>>> # Including Evaluation Results
>>> card_data = ModelCardData(
... language='en',
... tags=['image-classification', 'resnet'],
... eval_results=[
... EvalResult(
... task_type='image-classification',
... dataset_type='beans',
... dataset_name='Beans',
... metric_type='accuracy',
... metric_value=0.9,
... ),
... ],
... model_name='my-cool-model',
... )
>>> card = ModelCard.from_template(card_data)
>>> # Using a Custom Template
>>> card_data = ModelCardData(
... language='en',
... tags=['image-classification', 'resnet']
... )
>>> card = ModelCard.from_template(
... card_data=card_data,
... template_path='./src/huggingface_hub/templates/modelcard_template.md',
... custom_template_var='custom value', # will be replaced in template if it exists
... )
```
superr rd r r r r __class__s r$ r zModelCard.from_templateW s R w$Y
|___r& r )
r r r r rA r r r] r r rY r
__classcell__r s @r$ r r R s[ #O 3I (,&* H` H` }H` sm H` H`r& r c T e Zd ZeZeZdZe ddede e
de e
f fd
Z xZ S ) DatasetCarddatasetr r r c ( t | |||fi |S )a Initialize a DatasetCard from a template. By default, it uses the default template, which can be found here:
https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md
Templates are Jinja2 templates that can be customized by passing keyword arguments.
Args:
card_data (`huggingface_hub.DatasetCardData`):
A huggingface_hub.DatasetCardData instance containing the metadata you want to include in the YAML
header of the dataset card on the Hugging Face Hub.
template_path (`str`, *optional*):
A path to a markdown file with optional Jinja template variables that can be filled
in with `template_kwargs`. Defaults to the default template.
Returns:
[`huggingface_hub.DatasetCard`]: A DatasetCard instance with the specified card data and content from the
template.
Example:
```python
>>> from huggingface_hub import DatasetCard, DatasetCardData
>>> # Using the Default Template
>>> card_data = DatasetCardData(
... language='en',
... license='mit',
... annotations_creators='crowdsourced',
... task_categories=['text-classification'],
... task_ids=['sentiment-classification', 'text-scoring'],
... multilinguality='monolingual',
... pretty_name='My Text Classification Dataset',
... )
>>> card = DatasetCard.from_template(
... card_data,
... pretty_name=card_data.pretty_name,
... )
>>> # Using a Custom Template
>>> card_data = DatasetCardData(
... language='en',
... license='mit',
... )
>>> card = DatasetCard.from_template(
... card_data=card_data,
... template_path='./src/huggingface_hub/templates/datasetcard_template.md',
... custom_template_var='custom value', # will be replaced in template if it exists
... )
```
r r s r$ r zDatasetCard.from_template s r w$Y
|___r& r )
r r r r
rA TEMPLATE_DATASETCARD_PATHr r] r r rY r r r s @r$ r r sV %O 5I (,&* 8`"8` }8` sm 8` 8`r& r c e Zd ZeZeZdZy) SpaceCardspaceN)r r r r rA r r r] r5 r& r$ r r s #O 3Ir& r r return)
r(
Nc | j d }| j d }| j d }||z dk( ry||k( r||k( ry||kD ryy)zDetect the line ending of a string. Used by RepoCard to avoid making huge diff on newlines.
Uses same implementation as in Hub server, keep it in sync.
Returns:
str: The detected line ending of the string.
r r( r r N)count)r crlfcrlfs r$ r, r, sY
t B t B == D Bw!| rzdbj Bwr&
local_pathc t | j }t j | }|rE|j d }t j | }|t |t r|S t d y )Nr3 r4 )
r r r6 r7 r8 r: r; r< r= r> )r r rD rE r. s r$
metadata_loadr se : ((*G # #G ,E [[^
~~j) <:dD1KDEEr& r. c d}d}t j j | rxt | ddd 5 }|j }t |j t r|j d }n&t |j t r |j }ddd t | ddd 5 }t |d |
}t j | }|r3|d|j d | | d | z ||j d z }n d | | d | | }|j | |j ddd y# 1 sw Y xY w# 1 sw Y yxY w) a&
Save the metadata dict in the upper YAML part Trying to preserve newlines as
in the existing file. Docs about open() with newline="" parameter:
https://docs.python.org/3/library/functions.html?highlight=open#open Does
not work with "^M" linebreaks, which are replaced by
r( rO r` utf8)rS rT r NrN F) sort_keysr* r) )ospathra rW rc r< newlinestuplerY r r6 r7 startr9 rX close)r r. r* r readme data_yamlrD outputs r$
metadata_saver s0 JG ww~~j!
*c2
?6 kkmG&//51 #__Q /
FOOS1 #__
@
j#rF ;v de
K ''0 _u{{}-#j\)CPZ|0\\_fglgpgpgrgt_uuF:,ykZL JF V
< ; @
?
< ;s A!D:+BE:EEF)metrics_configmetrics_verifieddataset_config
dataset_splitdataset_revisionmetrics_verification_tokenmodel_pretty_nametask_pretty_nametask_idmetrics_pretty_name
metrics_id
metrics_valuedataset_pretty_name
dataset_idr r r r r r c N dt | t ||||||||| |
|
| |
g iS )u
Creates a metadata dict with the result from a model evaluated on a dataset.
Args:
model_pretty_name (`str`):
The name of the model in natural language.
task_pretty_name (`str`):
The name of a task in natural language.
task_id (`str`):
Example: automatic-speech-recognition. A task id.
metrics_pretty_name (`str`):
A name for the metric in natural language. Example: Test WER.
metrics_id (`str`):
Example: wer. A metric id from https://hf.co/metrics.
metrics_value (`Any`):
The value from the metric. Example: 20.0 or "20.0 ± 1.2".
dataset_pretty_name (`str`):
The name of the dataset in natural language.
dataset_id (`str`):
Example: common_voice. A dataset id from https://hf.co/datasets.
metrics_config (`str`, *optional*):
The name of the metric configuration used in `load_metric()`.
Example: bleurt-large-512 in `load_metric("bleurt", "bleurt-large-512")`.
metrics_verified (`bool`, *optional*, defaults to `False`):
Indicates whether the metrics originate from Hugging Face's [evaluation service](https://huggingface.co/spaces/autoevaluate/model-evaluator) or not. Automatically computed by Hugging Face, do not set.
dataset_config (`str`, *optional*):
Example: fr. The name of the dataset configuration used in `load_dataset()`.
dataset_split (`str`, *optional*):
Example: test. The name of the dataset split used in `load_dataset()`.
dataset_revision (`str`, *optional*):
Example: 5503434ddd753f426f4b38109466949a1217c2bb. The name of the dataset dataset revision
used in `load_dataset()`.
metrics_verification_token (`bool`, *optional*):
A JSON Web Token that is used to verify whether the metrics originate from Hugging Face's [evaluation service](https://huggingface.co/spaces/autoevaluate/model-evaluator) or not.
Returns:
`dict`: a metadata dict with the result from a model evaluated on a dataset.
Example:
```python
>>> from huggingface_hub import metadata_eval_result
>>> results = metadata_eval_result(
... model_pretty_name="RoBERTa fine-tuned on ReactionGIF",
... task_pretty_name="Text Classification",
... task_id="text-classification",
... metrics_pretty_name="Accuracy",
... metrics_id="accuracy",
... metrics_value=0.2662102282047272,
... dataset_pretty_name="ReactionJPEG",
... dataset_id="julien-c/reactionjpeg",
... dataset_config="default",
... dataset_split="test",
... )
>>> results == {
... 'model-index': [
... {
... 'name': 'RoBERTa fine-tuned on ReactionGIF',
... 'results': [
... {
... 'task': {
... 'type': 'text-classification',
... 'name': 'Text Classification'
... },
... 'dataset': {
... 'name': 'ReactionJPEG',
... 'type': 'julien-c/reactionjpeg',
... 'config': 'default',
... 'split': 'test'
... },
... 'metrics': [
... {
... 'type': 'accuracy',
... 'value': 0.2662102282047272,
... 'name': 'Accuracy',
... 'verified': False
... }
... ]
... }
... ]
... }
... ]
... }
True
```
model-index)
task_name task_type metric_name metric_type metric_value dataset_name dataset_type
metric_configverified verify_tokenr r r )
model_name eval_results)r r )r r r r r r r r r r r r r r s r$ metadata_eval_resultr , sQ R 2( . % 3 *!.!4!+"0 -!;#1"/%5
r& )r] overwriter^ ru rv rw rx ry rt metadatar] r r^ ru rv rw rx ry c
| ||nd}||dk( rt }
n&|dk( rt }
n|dk( rt }
nt d| |
j | || } |j D ] \ } }
| dk( r#d |
d
vrt | d | |
d
d < t |
\ }}| j j #|| j _ || j _
n| j j }|D ] }d }|D ]t }|j | s||k7 r(|s&t d
|j d|j d d}|j" |_ |j$ du sd|j& |_ v |r| j j j) | 0| j j+ | /|s-| j j+ | |
k7 rt d| d |
| j | < | j- | ||||||| S # t
$ r- |dk( r t d |
j
t } Y w xY w)a
Updates the metadata in the README.md of a repository on the Hugging Face Hub.
If the README.md file doesn't exist yet, a new one is created with metadata and an
the default ModelCard or DatasetCard template. For `space` repo, an error is thrown
as a Space cannot exist without a `README.md` file.
Args:
repo_id (`str`):
The name of the repository.
metadata (`dict`):
A dictionary containing the metadata to be updated.
repo_type (`str`, *optional*):
Set to `"dataset"` or `"space"` if updating to a dataset or space,
`None` or `"model"` if updating to a model. Default is `None`.
overwrite (`bool`, *optional*, defaults to `False`):
If set to `True` an existing field can be overwritten, otherwise
attempting to overwrite an existing field will cause an error.
token (`str`, *optional*):
The Hugging Face authentication token.
commit_message (`str`, *optional*):
The summary / title / first line of the generated commit. Defaults to
`f"Update metadata with huggingface_hub"`
commit_description (`str` *optional*)
The description of the generated commit
revision (`str`, *optional*):
The git revision to commit from. Defaults to the head of the
`"main"` branch.
create_pr (`boolean`, *optional*):
Whether or not to create a Pull Request from `revision` with that commit.
Defaults to `False`.
parent_commit (`str`, *optional*):
The OID / SHA of the parent commit, as a hexadecimal string. Shorthands (7 first characters) are also supported.
If specified and `create_pr` is `False`, the commit will fail if `revision` does not point to `parent_commit`.
If specified and `create_pr` is `True`, the pull request will be created from `parent_commit`.
Specifying `parent_commit` ensures the repo has not changed before committing the changes, and can be
especially useful if the repo is updated / committed to concurrently.
Returns:
`str`: URL of the commit which updated the card metadata.
Example:
```python
>>> from huggingface_hub import metadata_update
>>> metadata = {'model-index': [{'name': 'RoBERTa fine-tuned on ReactionGIF',
... 'results': [{'dataset': {'name': 'ReactionGIF',
... 'type': 'julien-c/reactiongif'},
... 'metrics': [{'name': 'Recall',
... 'type': 'recall',
... 'value': 0.7762102282047272}],
... 'task': {'name': 'Text Classification',
... 'type': 'text-classification'}}]}]}
>>> url = metadata_update("hf-internal-testing/reactiongif-roberta-card", metadata)
```
z$Update metadata with huggingface_hubr r r zUnknown repo_type: )r^ r] zJCannot update metadata on a Space that doesn't contain a `README.md` file.r namer r Fz6You passed a new value for the existing metric 'name: z, type: z6'. Set `overwrite=True` to overwrite existing metrics.Tz9You passed a new value for the existing meta data field 'z7'. Set `overwrite=True` to overwrite existing metadata.)r^ r] ru rv rx rw ry )r r r r> rf r r r itemsgetattrr r. r r is_equal_except_valuer r r r r appendgetr )rt r r] r r^ ru rv rw rx ry
card_classcardkeyvaluer new_resultsexisting_results
new_result result_foundexisting_results r$ metadata_updater sz H (6'A^GmN I 0
i
g
.yk:;;4weyI nn&
U - U1X%#*4 w#Ga &A%&H #J yy%%-)4 &'1 $#'99#9#9 #.J#(L+;%;;OL )_ r s < < 9 . M L & H H
H % x.//+=@WW N 1 1K ?B[ [ 2:: RS i i X N` N`b>`( >`B 1I)J *
eCI .
8D>
eCI . d t T %) "$(#'&*04 }} } }
}
} } } } SM} } SM} C=} sm } !)
}
!}@
$ $((, "#'Q
QQ } Q
Q C=
Q SMQ !
Q smQ Q C=Q Q Qr&