Add model card (#1)

31a5a94 almost 2 years ago

No virus

5.78 kB

	---
	language:
	- multilingual
	- en
	- fr
	license: cc-by-nc-4.0
	---

	# xlm-mlm-enfr-1024

	# Table of Contents

	1. [Model Details](#model-details)
	2. [Uses](#uses)
	3. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
	4. [Training](#training)
	5. [Evaluation](#evaluation)
	6. [Environmental Impact](#environmental-impact)
	7. [Technical Specifications](#technical-specifications)
	8. [Citation](#citation)
	9. [Model Card Authors](#model-card-authors)
	10. [How To Get Started With the Model](#how-to-get-started-with-the-model)


	# Model Details

	The XLM model was proposed in [Cross-lingual Language Model Pretraining](https://arxiv.org/abs/1901.07291) by Guillaume Lample, Alexis Conneau. xlm-mlm-enfr-1024 is a transformer pretrained using a masked language modeling (MLM) objective for English-French. This model uses language embeddings to specify the language used at inference. See the [Hugging Face Multilingual Models for Inference docs](https://huggingface.co/docs/transformers/v4.20.1/en/multilingual#xlm-with-language-embeddings) for further details.

	## Model Description

	- Developed by: Guillaume Lample, Alexis Conneau, see [associated paper](https://arxiv.org/abs/1901.07291)
	- Model type: Language model
	- Language(s) (NLP): English-French
	- License: CC-BY-NC-4.0
	- Related Models: [xlm-clm-ende-1024](https://huggingface.co/xlm-clm-enfr-1024), [xlm-clm-ende-1024](https://huggingface.co/xlm-clm-ende-1024), [xlm-mlm-ende-1024](https://huggingface.co/xlm-mlm-ende-1024), [xlm-mlm-enro-1024](https://huggingface.co/xlm-mlm-enro-1024)
	- Resources for more information:
	- [Associated paper](https://arxiv.org/abs/1901.07291)
	- [GitHub Repo](https://github.com/facebookresearch/XLM)
	- [Hugging Face Multilingual Models for Inference docs](https://huggingface.co/docs/transformers/v4.20.1/en/multilingual#xlm-with-language-embeddings)

	# Uses

	## Direct Use

	The model is a language model. The model can be used for masked language modeling.

	## Downstream Use

	To learn more about this task and potential downstream uses, see the Hugging Face [fill mask docs](https://huggingface.co/tasks/fill-mask) and the [Hugging Face Multilingual Models for Inference](https://huggingface.co/docs/transformers/v4.20.1/en/multilingual#xlm-with-language-embeddings) docs.

	## Out-of-Scope Use

	The model should not be used to intentionally create hostile or alienating environments for people.

	# Bias, Risks, and Limitations

	Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).

	## Recommendations

	Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

	# Training

	The model developers write:

	> In all experiments, we use a Transformer architecture with 1024 hidden units, 8 heads, GELU activations (Hendrycks and Gimpel, 2016), a dropout rate of 0.1 and learned positional embeddings. We train our models with the Adam op- timizer (Kingma and Ba, 2014), a linear warm- up (Vaswani et al., 2017) and learning rates varying from 10^−4 to 5.10^−4.

	See the [associated paper](https://arxiv.org/pdf/1901.07291.pdf) for links, citations, and further details on the training data and training procedure.

	The model developers also write that:

	> If you use these models, you should use the same data preprocessing / BPE codes to preprocess your data.

	See the associated [GitHub Repo](https://github.com/facebookresearch/XLM#ii-cross-lingual-language-model-pretraining-xlm) for further details.

	# Evaluation

	## Testing Data, Factors & Metrics

	The model developers evaluated the model on the [WMT'14 English-French](https://huggingface.co/datasets/wmt14) dataset using the [BLEU metric](https://huggingface.co/spaces/evaluate-metric/bleu). See the [associated paper](https://arxiv.org/pdf/1901.07291.pdf) for further details on the testing data, factors and metrics.

	## Results

	For xlm-mlm-enfr-1024 results, see Table 1 and Table 2 of the [associated paper](https://arxiv.org/pdf/1901.07291.pdf).

	# Environmental Impact

	Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

	- Hardware Type: More information needed
	- Hours used: More information needed
	- Cloud Provider: More information needed
	- Compute Region: More information needed
	- Carbon Emitted: More information needed

	# Technical Specifications

	The model developers write:

	> We implement all our models in PyTorch (Paszke et al., 2017), and train them on 64 Volta GPUs for the language modeling tasks, and 8 GPUs for the MT tasks. We use float16 operations to speed up training and to reduce the memory usage of our models.

	See the [associated paper](https://arxiv.org/pdf/1901.07291.pdf) for further details.

	# Citation

	BibTeX:

	```bibtex
	@article{lample2019cross,
	title={Cross-lingual language model pretraining},
	author={Lample, Guillaume and Conneau, Alexis},
	journal={arXiv preprint arXiv:1901.07291},
	year={2019}
	}
	```

	APA:
	- Lample, G., & Conneau, A. (2019). Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291.

	# Model Card Authors

	This model card was written by the team at Hugging Face.

	# How to Get Started with the Model

	More information needed. This model uses language embeddings to specify the language used at inference. See the [Hugging Face Multilingual Models for Inference docs](https://huggingface.co/docs/transformers/v4.20.1/en/multilingual#xlm-with-language-embeddings) for further details.