Getting Started With Hugging Face-Installation and setUp

Hub Client Library :

The huggingface_hub library allows us to interact with Hugging FaceHub wich is a ML platform .There are hundreds of pre trained models and datasets hosted on te hub.The models and datasets that are created by u also can be hosted.

It mostly deals with PYTHON

INSTALLATION:

To install Hugging Face :

pip install git+https://github.com/huggingface/huggingface_hub        

Repositories on the Hub are git version controlled, and we can download a single file or the whole repository.The files are downloaded with the "hf_hub_download()".This function will download and cache a file on our local disk.

from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="google/pegasus-xsum", filename="config.json")        

Login

In a lot of cases, we must be logged in with a Hugging Face account to interact with the Hub such as download private repos, upload files and so on.

huggingface-cli login 
huggingface-cli login --token $HUGGINGFACE_TOKEN        

OR

We can programmatically login using?login()?in a notebook or a script:

from huggingface_hub import login
login()        

Create a repository

In order to create repo()

from huggingface_hub import HfApi
api = HfApi()
api.create_repo(repo_id="super-cool-model")        

Download files

Repositories on the Hub are git version controlled, and users can download a single file or the whole repository.? the?hf_hub_download()?function can be used to download files. This function will download and cache a file on your local disk.

the repository id and the filename of the file are required to download.

Example consider Pegasus model config gile:

Pegasus:

• Pegasus’ pretraining task is intentionally similar to summarization: important sentences are removed/masked from an input document and are generated together as one output sequence from the remaining sentences, similar to an extractive summary.
• Pegasus achieves SOTA summarization performance on all 12 downstream tasks, as measured by ROUGE and human eval.

Tips:

• Sequence-to-sequence model with the same encoder-decoder model architecture as BART. Pegasus is pre-trained jointly on two self-supervised objective functions: Masked Language Modeling (MLM) and a novel summarization specific pretraining objective, called Gap Sentence Generation (GSG).
• MLM: encoder input tokens are randomly replaced by a mask tokens and have to be predicted by the encoder (like in BERT)
• GSG: whole encoder input sentences are replaced by a second mask token and fed to the decoder, but which has a causal mask to hide the future words like a regular auto-regressive transformer decoder.

from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="google/pegasus-xsum", filename="config.json")        

Upload files

To upload files use upload_file()

The following things should be mentioned:

1.Path to the file to upload

2.The path of the file in repo

3.The repo id of where we wanna add the file .

from huggingface_hub import HfApi 
api = HfApi()
api.upload_file(
path_or_fileobj ="/home/dir/...",
path_in_repo = "Readme.md",
repo_id = "username/test_dataset"
)        

Installation

Install with pip

pip install --upgrade huggingface_hub        

Install optional dependencies

pip install 'huggingface_hub[tensorflow]'        

pip install 'huggingface_hub[cli,torch]'
        

Install from source

pip install git+https://github.com/huggingface/huggingface_hub

or
        

pip install git+https://github.com/huggingface/huggingface_hub@my-feature-branch        

Editable install

git clone https://github.com/huggingface/huggingface_hub.git

cd huggingface_hub
pip install -e .        

Installing with Conda

conda install -c conda-forge huggingface_hub        

Conclusion:

This article includes what is hugging ce and the installationa and the setup.Th following articles will cover more concepts related to Hgging Face.