SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Small cosmetic changes to CamemBERT model card

Browse Source
This commit is contained in:
Louis MARTIN
2020-04-18 02:53:45 -07:00
committed by Julien Chaumond
parent 4a94c062a4
commit c73c83b0e6
1 changed files with 12 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
model_cards/camembert-base-README.md
View File

@@ -6,9 +6,9 @@ language: french
## Introduction ## Introduction
[CamemBERT](https://arxiv.org/abs/1911.03894) is a state-of-the-art language model for French based on the RoBERTa architecture. [CamemBERT](https://arxiv.org/abs/1911.03894) is a state-of-the-art language model for French based on the RoBERTa model.
It is now available on Hugging Face in 6 different versions varying the number of parameters, the amount of pretraining data and the pretraining data source domains. It is now available on Hugging Face in 6 different versions with varying number of parameters, amount of pretraining data and pretraining data source domains.
For further information or requests, please go to [Camembert Website](https://camembert-model.fr/) For further information or requests, please go to [Camembert Website](https://camembert-model.fr/)
@@ -17,11 +17,11 @@ For further information or requests, please go to [Camembert Website](https://ca
| Model | #params | Arch. | Training data | | Model | #params | Arch. | Training data |
|--------------------------------|--------------------------------|-------|-----------------------------------| |--------------------------------|--------------------------------|-------|-----------------------------------|
| `camembert-base` | 110M | Base | OSCAR (138 GB of text) | | `camembert-base` | 110M | Base | OSCAR (138 GB of text) |
| `camembert` / `camembert-large` | 335M | Large | CCNet (135 GB of text) | | `camembert/camembert-large` | 335M | Large | CCNet (135 GB of text) |
| `camembert` / `camembert-base-ccnet` | 110M | Base | CCNet (135 GB of text) | | `camembert/camembert-base-ccnet` | 110M | Base | CCNet (135 GB of text) |
| `camembert` / `camembert-base-wikipedia-4gb` | 110M | Base | Wikipedia (4 GB of text) | | `camembert/camembert-base-wikipedia-4gb` | 110M | Base | Wikipedia (4 GB of text) |
| `camembert` / `camembert-base-oscar-4gb` | 110M | Base | Subsample of OSCAR (4 GB of text) | | `camembert/camembert-base-oscar-4gb` | 110M | Base | Subsample of OSCAR (4 GB of text) |
| `camembert` / `camembert-base-ccnet-4gb` | 110M | Base | Subsample of CCNet (4 GB of text) | | `camembert/camembert-base-ccnet-4gb` | 110M | Base | Subsample of CCNet (4 GB of text) |
## How to use CamemBERT with HuggingFace ## How to use CamemBERT with HuggingFace
@@ -29,6 +29,7 @@ For further information or requests, please go to [Camembert Website](https://ca
```python ```python
from transformers import CamembertModel, CamembertTokenizer from transformers import CamembertModel, CamembertTokenizer
# You can replace "camembert-base" with any other model from the table, e.g. "camembert/camembert-large".
tokenizer = CamembertTokenizer.from_pretrained("camembert-base") tokenizer = CamembertTokenizer.from_pretrained("camembert-base")
camembert = CamembertModel.from_pretrained("camembert-base") camembert = CamembertModel.from_pretrained("camembert-base")
@@ -61,9 +62,9 @@ tokenized_sentence = tokenizer.tokenize("J'aime le camembert !")
# 1-hot encode and add special starting and end tokens # 1-hot encode and add special starting and end tokens
encoded_sentence = tokenizer.encode(tokenized_sentence) encoded_sentence = tokenizer.encode(tokenized_sentence)
# [5, 121, 11, 660, 16, 730, 25543, 110, 83, 6] # [5, 121, 11, 660, 16, 730, 25543, 110, 83, 6]
# NB: can do in one step : tokenize.encode("J'aime le camembert !") # NB: Can be done in one step : tokenize.encode("J'aime le camembert !")
# Feed to Camembert as a torch tensor (batch dim 1) # Feed tokens to Camembert as a torch tensor (batch dim 1)
encoded_sentence = torch.tensor(encoded_sentence).unsqueeze(0) encoded_sentence = torch.tensor(encoded_sentence).unsqueeze(0)
embeddings, _ = camembert(encoded_sentence) embeddings, _ = camembert(encoded_sentence)
# embeddings.detach() # embeddings.detach()