From fa9365eca54e6093a59b5eee2904bcb2b960c55d Mon Sep 17 00:00:00 2001 From: Benjamin Muller Date: Wed, 29 Apr 2020 11:38:47 +0800 Subject: [PATCH] Create README.md --- .../camembert-base-oscar-4gb/README.md | 111 ++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 model_cards/camembert/camembert-base-oscar-4gb/README.md diff --git a/model_cards/camembert/camembert-base-oscar-4gb/README.md b/model_cards/camembert/camembert-base-oscar-4gb/README.md new file mode 100644 index 0000000000..cf6035bfa1 --- /dev/null +++ b/model_cards/camembert/camembert-base-oscar-4gb/README.md @@ -0,0 +1,111 @@ +--- +language: french +--- + +# CamemBERT: a Tasty French Language Model + +## Introduction + +[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 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/) + +## Pre-trained models + +| Model | #params | Arch. | Training data | +|--------------------------------|--------------------------------|-------|-----------------------------------| +| `camembert-base` | 110M | Base | OSCAR (138 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-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-ccnet-4gb` | 110M | Base | Subsample of CCNet (4 GB of text) | + +## How to use CamemBERT with HuggingFace + +##### Load CamemBERT and its sub-word tokenizer : +```python +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/camembert-base-oscar-4gb") +camembert = CamembertModel.from_pretrained("camembert/camembert-base-oscar-4gb") + +camembert.eval() # disable dropout (or leave in train mode to finetune) + +``` + +##### Filling masks using pipeline +```python +from transformers import pipeline + +camembert_fill_mask = pipeline("fill-mask", model="camembert/camembert-base-oscar-4gb", tokenizer="camembert/camembert-base-oscar-4gb") +>>> results = camembert_fill_mask("Le camembert est !") +# results +#[{'sequence': ' Le camembert est parfait!', 'score': 0.04089554399251938, 'token': 1654}, +#{'sequence': ' Le camembert est délicieux!', 'score': 0.037193264812231064, 'token': 7200}, +#{'sequence': ' Le camembert est prêt!', 'score': 0.025467922911047935, 'token': 1415}, +#{'sequence': ' Le camembert est meilleur!', 'score': 0.022812040522694588, 'token': 528}, +#{'sequence': ' Le camembert est différent!', 'score': 0.017135459929704666, 'token': 2935}] + +``` + +##### Extract contextual embedding features from Camembert output +```python +import torch +# Tokenize in sub-words with SentencePiece +tokenized_sentence = tokenizer.tokenize("J'aime le camembert !") +# ['▁J', "'", 'aime', '▁le', '▁ca', 'member', 't', '▁!'] + +# 1-hot encode and add special starting and end tokens +encoded_sentence = tokenizer.encode(tokenized_sentence) +# [5, 121, 11, 660, 16, 730, 25543, 110, 83, 6] +# NB: Can be done in one step : tokenize.encode("J'aime le camembert !") + +# Feed tokens to Camembert as a torch tensor (batch dim 1) +encoded_sentence = torch.tensor(encoded_sentence).unsqueeze(0) +embeddings, _ = camembert(encoded_sentence) +# embeddings.detach() +# embeddings.size torch.Size([1, 10, 768]) +#tensor([[[-0.1120, -0.1464, 0.0181, ..., -0.1723, -0.0278, 0.1606], +# [ 0.1234, 0.1202, -0.0773, ..., -0.0405, -0.0668, -0.0788], +# [-0.0440, 0.0480, -0.1926, ..., 0.1066, -0.0961, 0.0637], +# ..., +``` + +##### Extract contextual embedding features from all Camembert layers +```python +from transformers import CamembertConfig +# (Need to reload the model with new config) +config = CamembertConfig.from_pretrained("camembert/camembert-base-oscar-4gb", output_hidden_states=True) +camembert = CamembertModel.from_pretrained("camembert/camembert-base-oscar-4gb", config=config) + +embeddings, _, all_layer_embeddings = camembert(encoded_sentence) +# all_layer_embeddings list of len(all_layer_embeddings) == 13 (input embedding layer + 12 self attention layers) +all_layer_embeddings[5] +# layer 5 contextual embedding : size torch.Size([1, 10, 768]) +#tensor([[[-0.1584, -0.1207, -0.0179, ..., 0.5457, 0.1491, -0.1191], +# [-0.1122, 0.3634, 0.0676, ..., 0.4395, -0.0470, -0.3781], +# [-0.2232, 0.0019, 0.0140, ..., 0.4461, -0.0233, 0.0735], +# ..., +``` + + +## Authors + +CamemBERT was trained and evaluated by Louis Martin\*, Benjamin Muller\*, Pedro Javier Ortiz Suárez\*, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah and Benoît Sagot. + + +## Citation +If you use our work, please cite: + +```bibtex +@inproceedings{martin2020camembert, + title={CamemBERT: a Tasty French Language Model}, + author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t}, + booktitle={Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}, + year={2020} +} +```