GPT2 Models
Collection
All gpt2 models were trained from scratch
•
3 items
•
Updated
Description
This is the polish gpt2 model in medium architecture.
This model was released on 30.11.2023.
Datasets
Data which are used to train this model:
- clarin-knext/msmarco-pl
- clarin-knext/nq-pl
- clarin-knext/hotpotqa-pl
- clarin-knext/scidocs-pl
- clarin-knext/nfcorpus-pl
- clarin-knext/dbpedia-pl
- clarin-knext/trec-covid-pl
- clarin-knext/quora-pl
- clarin-knext/arguana-pl
- clarin-knext/fiqa-pl
- radlab/wikipedia-pl
- radlab/legal-mc4-pl
- own corpora not published yet
It is about 30,5 GB of data which is 3 times more than the prevoius version.
Metrics from W&B
Changelog
- 2023.11.30 - publishing the first version of the model
- Downloads last month
- 483
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.