Statements (27)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
large language model
|
| gptkbp:application |
question answering
part-of-speech tagging text classification named entity recognition |
| gptkbp:architecture |
gptkb:transformation
|
| gptkbp:basedOn |
gptkb:RoBERTa
|
| gptkbp:developedBy |
gptkb:INRIA
gptkb:Facebook_AI_Research |
| https://www.w3.org/2000/01/rdf-schema#label |
CamemBERT
|
| gptkbp:input |
gptkb:text
|
| gptkbp:language |
gptkb:French
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:notablePublication |
CamemBERT: a Tasty French Language Model
https://arxiv.org/abs/1911.03894 |
| gptkbp:openSource |
true
|
| gptkbp:output |
vector embeddings
|
| gptkbp:parameter |
110 million
|
| gptkbp:releaseYear |
2019
|
| gptkbp:supports |
transfer learning
fine-tuning |
| gptkbp:tokenizer |
gptkb:Byte-Pair_Encoding
|
| gptkbp:trainer |
gptkb:French_Wikipedia
French language understanding OSCAR corpus |
| gptkbp:bfsParent |
gptkb:Hugging_Face_models
|
| gptkbp:bfsLayer |
7
|