Papers
To ease the reproduction of papers, and the upload of full models on HuggingFace, the xpmir.papers package can be used.
Configuration
Papers experimental parameters are defined by data classes. The main
one is xpmir.papers.helpers.PaperExperiment
that
defines an id (for experimaestro), a title and a description.
These informations can be used e.g. when uploading the trained
models on HuggingFace.
- class xpmir.papers.helpers.PaperExperiment(*, id: str = '???', title: str = '', description: str = '')[source]
Bases:
object
- description: str
A description of the model
This description is used to generate reports
- id: str
The experiment ID
The ID should be unique, and might be used when exporting the model e.g. to HuggingFace
- title: str
The model title
The title is used to generate report
- class xpmir.papers.helpers.NeuralIRExperiment(*, id: str = '???', title: str = '', description: str = '', gpu: bool = True, seed: int = 0)[source]
Bases:
PaperExperiment
Settings most neural IR experiments
- description: str
A description of the model
This description is used to generate reports
- gpu: bool
Use GPU for computation
- id: str
The experiment ID
The ID should be unique, and might be used when exporting the model e.g. to HuggingFace
- seed: int
The seed used for experiments
- title: str
The model title
The title is used to generate report
Helpers
Pipelines factorize the code necessary to run some experiments: for instance, training re-rankers on MS-Marco is usually performed with similar training data, evaluation datasets.
Implemented papers
This page give some information about reproduction of papers based on XPMIR.
-
monoBERT