Updated the Model docs - for the MARIAN model (#39138)
* Update marian.md This update improves the Marian model card to follow the Hugging Face standardized model card format. The changes include: - Added a clear description of MarianMT, its architecture, and how it differs from other models. - Provided usage examples for Pipeline and AutoModel. - Added a quantization example for optimizing model inference. - Included instructions and examples for multilingual translation with language codes. - Added an Attention Mask Visualizer example. - Added a Resources section with relevant links to papers, the Marian framework, language codes, tokenizer guides, and quantization documentation. - Fixed formatting issues in the code blocks for correct rendering. This update improves the readability, usability, and consistency of the Marian model documentation for users. * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update marian.md * Update marian.md * Update marian.md * Update marian.md * Update docs/source/en/model_doc/marian.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update marian.md * Update marian.md * Update marian.md * Update marian.md --------- Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
This commit is contained in:
Eman Risha
@@ -14,159 +14,138 @@ rendered properly in your Markdown viewer.
|
|||||||
|
|
||||||
-->
|
-->
|
||||||
|
|
||||||
# MarianMT
|
<div style="float: right;">
|
||||||
|
<div class="flex flex-wrap space-x-1">
|
||||||
<div class="flex flex-wrap space-x-1">
|
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white">
|
||||||
<img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white">
|
<img alt="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white">
|
||||||
<img alt="TensorFlow" src="https://img.shields.io/badge/TensorFlow-FF6F00?style=flat&logo=tensorflow&logoColor=white">
|
<img alt="Flax" src="https://img.shields.io/badge/Flax-29a79b.svg?style=flat&logo=data:image/png;base64,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
|
||||||
<img alt="Flax" src="https://img.shields.io/badge/Flax-29a79b.svg?style=flat&logo=data:image/png;base64,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
|
|
||||||
">
|
">
|
||||||
<img alt="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
|
<img alt="FlashAttention" src="https://img.shields.io/badge/%E2%9A%A1%EF%B8%8E%20FlashAttention-eae0c8?style=flat">
|
||||||
<img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
|
<img alt="SDPA" src="https://img.shields.io/badge/SDPA-DE3412?style=flat&logo=pytorch&logoColor=white">
|
||||||
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
## Overview
|
# MarianMT
|
||||||
|
|
||||||
A framework for translation models, using the same models as BART. Translations should be similar, but not identical to output in the test set linked to in each model card.
|
|
||||||
This model was contributed by [sshleifer](https://huggingface.co/sshleifer).
|
|
||||||
|
|
||||||
|
|
||||||
## Implementation Notes
|
|
||||||
|
|
||||||
- Each model is about 298 MB on disk, there are more than 1,000 models.
|
[MarianMT](https://huggingface.co/papers/1804.00344) is a machine translation model trained with the Marian framework which is written in pure C++. The framework includes its own custom auto-differentiation engine and efficient meta-algorithms to train encoder-decoder models like BART.
|
||||||
- The list of supported language pairs can be found [here](https://huggingface.co/Helsinki-NLP).
|
|
||||||
- Models were originally trained by [Jörg Tiedemann](https://researchportal.helsinki.fi/en/persons/j%C3%B6rg-tiedemann) using the [Marian](https://marian-nmt.github.io/) C++ library, which supports fast training and translation.
|
|
||||||
- All models are transformer encoder-decoders with 6 layers in each component. Each model's performance is documented
|
|
||||||
in a model card.
|
|
||||||
- The 80 opus models that require BPE preprocessing are not supported.
|
|
||||||
- The modeling code is the same as [`BartForConditionalGeneration`] with a few minor modifications:
|
|
||||||
|
|
||||||
- static (sinusoid) positional embeddings (`MarianConfig.static_position_embeddings=True`)
|
All MarianMT models are transformer encoder-decoders with 6 layers in each component, use static sinusoidal positional embeddings, don't have a layernorm embedding, and the model starts generating with the prefix `pad_token_id` instead of `<s/>`.
|
||||||
- no layernorm_embedding (`MarianConfig.normalize_embedding=False`)
|
|
||||||
- the model starts generating with `pad_token_id` (which has 0 as a token_embedding) as the prefix (Bart uses
|
|
||||||
`<s/>`),
|
|
||||||
- Code to bulk convert models can be found in `convert_marian_to_pytorch.py`.
|
|
||||||
|
|
||||||
|
|
||||||
## Naming
|
|
||||||
|
|
||||||
- All model names use the following format: `Helsinki-NLP/opus-mt-{src}-{tgt}`
|
You can find all the original MarianMT checkpoints under the [Language Technology Research Group at the University of Helsinki](https://huggingface.co/Helsinki-NLP/models?search=opus-mt) organization.
|
||||||
- The language codes used to name models are inconsistent. Two digit codes can usually be found [here](https://developers.google.com/admin-sdk/directory/v1/languages), three digit codes require googling "language
|
|
||||||
code {code}".
|
|
||||||
- Codes formatted like `es_AR` are usually `code_{region}`. That one is Spanish from Argentina.
|
|
||||||
- The models were converted in two stages. The first 1000 models use ISO-639-2 codes to identify languages, the second
|
|
||||||
group use a combination of ISO-639-5 codes and ISO-639-2 codes.
|
|
||||||
|
|
||||||
|
|
||||||
## Examples
|
> [!TIP]
|
||||||
|
> This model was contributed by [sshleifer](https://huggingface.co/sshleifer).
|
||||||
|
>
|
||||||
|
> Click on the MarianMT models in the right sidebar for more examples of how to apply MarianMT to translation tasks.
|
||||||
|
|
||||||
- Since Marian models are smaller than many other translation models available in the library, they can be useful for
|
|
||||||
fine-tuning experiments and integration tests.
|
|
||||||
- [Fine-tune on GPU](https://github.com/huggingface/transformers/blob/master/examples/legacy/seq2seq/train_distil_marian_enro.sh)
|
|
||||||
|
|
||||||
## Multilingual Models
|
The example below demonstrates how to translate text using [`Pipeline`] or the [`AutoModel`] class.
|
||||||
|
|
||||||
- All model names use the following format: `Helsinki-NLP/opus-mt-{src}-{tgt}`:
|
<hfoptions id="usage">
|
||||||
- If a model can output multiple languages, and you should specify a language code by prepending the desired output
|
<hfoption id="Pipeline">
|
||||||
language to the `src_text`.
|
|
||||||
- You can see a models's supported language codes in its model card, under target constituents, like in [opus-mt-en-roa](https://huggingface.co/Helsinki-NLP/opus-mt-en-roa).
|
|
||||||
- Note that if a model is only multilingual on the source side, like `Helsinki-NLP/opus-mt-roa-en`, no language
|
|
||||||
codes are required.
|
|
||||||
|
|
||||||
New multi-lingual models from the [Tatoeba-Challenge repo](https://github.com/Helsinki-NLP/Tatoeba-Challenge)
|
|
||||||
require 3 character language codes:
|
|
||||||
|
|
||||||
```python
|
```python
|
||||||
>>> from transformers import MarianMTModel, MarianTokenizer
|
|
||||||
|
|
||||||
>>> src_text = [
|
import torch
|
||||||
... ">>fra<< this is a sentence in english that we want to translate to french",
|
from transformers import pipeline
|
||||||
... ">>por<< This should go to portuguese",
|
|
||||||
... ">>esp<< And this to Spanish",
|
|
||||||
... ]
|
|
||||||
|
|
||||||
>>> model_name = "Helsinki-NLP/opus-mt-en-roa"
|
pipeline = pipeline("translation_en_to_de", model="Helsinki-NLP/opus-mt-en-de", torch_dtype=torch.float16, device=0)
|
||||||
>>> tokenizer = MarianTokenizer.from_pretrained(model_name)
|
pipeline("Hello, how are you?")
|
||||||
>>> print(tokenizer.supported_language_codes)
|
|
||||||
['>>zlm_Latn<<', '>>mfe<<', '>>hat<<', '>>pap<<', '>>ast<<', '>>cat<<', '>>ind<<', '>>glg<<', '>>wln<<', '>>spa<<', '>>fra<<', '>>ron<<', '>>por<<', '>>ita<<', '>>oci<<', '>>arg<<', '>>min<<']
|
|
||||||
|
|
||||||
>>> model = MarianMTModel.from_pretrained(model_name)
|
|
||||||
>>> translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
|
|
||||||
>>> [tokenizer.decode(t, skip_special_tokens=True) for t in translated]
|
|
||||||
["c'est une phrase en anglais que nous voulons traduire en français",
|
|
||||||
'Isto deve ir para o português.',
|
|
||||||
'Y esto al español']
|
|
||||||
```
|
```
|
||||||
|
|
||||||
Here is the code to see all available pretrained models on the hub:
|
</hfoption>
|
||||||
|
|
||||||
|
<hfoption id="AutoModel">
|
||||||
|
|
||||||
```python
|
```python
|
||||||
from huggingface_hub import list_models
|
|
||||||
|
|
||||||
model_list = list_models()
|
import torch
|
||||||
org = "Helsinki-NLP"
|
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
||||||
model_ids = [x.id for x in model_list if x.id.startswith(org)]
|
|
||||||
suffix = [x.split("/")[1] for x in model_ids]
|
tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-de")
|
||||||
old_style_multi_models = [f"{org}/{s}" for s in suffix if s != s.lower()]
|
model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-en-de", torch_dtype=torch.float16, attn_implementation="sdpa", device_map="auto")
|
||||||
|
|
||||||
|
inputs = tokenizer("Hello, how are you?", return_tensors="pt").to("cuda")
|
||||||
|
outputs = model.generate(**inputs, cache_implementation="static")
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
|
||||||
```
|
```
|
||||||
|
|
||||||
## Old Style Multi-Lingual Models
|
</hfoption>
|
||||||
|
</hfoptions>
|
||||||
|
|
||||||
These are the old style multi-lingual models ported from the OPUS-MT-Train repo: and the members of each language
|
|
||||||
group:
|
|
||||||
|
|
||||||
```python no-style
|
|
||||||
['Helsinki-NLP/opus-mt-NORTH_EU-NORTH_EU',
|
|
||||||
'Helsinki-NLP/opus-mt-ROMANCE-en',
|
|
||||||
'Helsinki-NLP/opus-mt-SCANDINAVIA-SCANDINAVIA',
|
|
||||||
'Helsinki-NLP/opus-mt-de-ZH',
|
|
||||||
'Helsinki-NLP/opus-mt-en-CELTIC',
|
|
||||||
'Helsinki-NLP/opus-mt-en-ROMANCE',
|
|
||||||
'Helsinki-NLP/opus-mt-es-NORWAY',
|
|
||||||
'Helsinki-NLP/opus-mt-fi-NORWAY',
|
|
||||||
'Helsinki-NLP/opus-mt-fi-ZH',
|
|
||||||
'Helsinki-NLP/opus-mt-fi_nb_no_nn_ru_sv_en-SAMI',
|
|
||||||
'Helsinki-NLP/opus-mt-sv-NORWAY',
|
|
||||||
'Helsinki-NLP/opus-mt-sv-ZH']
|
|
||||||
GROUP_MEMBERS = {
|
|
||||||
'ZH': ['cmn', 'cn', 'yue', 'ze_zh', 'zh_cn', 'zh_CN', 'zh_HK', 'zh_tw', 'zh_TW', 'zh_yue', 'zhs', 'zht', 'zh'],
|
|
||||||
'ROMANCE': ['fr', 'fr_BE', 'fr_CA', 'fr_FR', 'wa', 'frp', 'oc', 'ca', 'rm', 'lld', 'fur', 'lij', 'lmo', 'es', 'es_AR', 'es_CL', 'es_CO', 'es_CR', 'es_DO', 'es_EC', 'es_ES', 'es_GT', 'es_HN', 'es_MX', 'es_NI', 'es_PA', 'es_PE', 'es_PR', 'es_SV', 'es_UY', 'es_VE', 'pt', 'pt_br', 'pt_BR', 'pt_PT', 'gl', 'lad', 'an', 'mwl', 'it', 'it_IT', 'co', 'nap', 'scn', 'vec', 'sc', 'ro', 'la'],
|
|
||||||
'NORTH_EU': ['de', 'nl', 'fy', 'af', 'da', 'fo', 'is', 'no', 'nb', 'nn', 'sv'],
|
|
||||||
'SCANDINAVIA': ['da', 'fo', 'is', 'no', 'nb', 'nn', 'sv'],
|
|
||||||
'SAMI': ['se', 'sma', 'smj', 'smn', 'sms'],
|
|
||||||
'NORWAY': ['nb_NO', 'nb', 'nn_NO', 'nn', 'nog', 'no_nb', 'no'],
|
|
||||||
'CELTIC': ['ga', 'cy', 'br', 'gd', 'kw', 'gv']
|
|
||||||
}
|
|
||||||
```
|
|
||||||
|
|
||||||
Example of translating english to many romance languages, using old-style 2 character language codes
|
|
||||||
|
|
||||||
|
Use the [AttentionMaskVisualizer](https://github.com/huggingface/transformers/blob/beb9b5b02246b9b7ee81ddf938f93f44cfeaad19/src/transformers/utils/attention_visualizer.py#L139) to better understand what tokens the model can and cannot attend to.
|
||||||
|
|
||||||
```python
|
```python
|
||||||
>>> from transformers import MarianMTModel, MarianTokenizer
|
from transformers.utils.attention_visualizer import AttentionMaskVisualizer
|
||||||
|
|
||||||
>>> src_text = [
|
visualizer = AttentionMaskVisualizer("Helsinki-NLP/opus-mt-en-de")
|
||||||
... ">>fr<< this is a sentence in english that we want to translate to french",
|
visualizer("Hello, how are you?")
|
||||||
... ">>pt<< This should go to portuguese",
|
```
|
||||||
... ">>es<< And this to Spanish",
|
<div class="flex justify-center">
|
||||||
... ]
|
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/marianmt-attn-mask.png"/>
|
||||||
|
</div>
|
||||||
|
|
||||||
>>> model_name = "Helsinki-NLP/opus-mt-en-ROMANCE"
|
## Notes
|
||||||
>>> tokenizer = MarianTokenizer.from_pretrained(model_name)
|
|
||||||
|
- MarianMT models are ~298MB on disk and there are more than 1000 models. Check this [list](https://huggingface.co/Helsinki-NLP) for supported language pairs. The language codes may be inconsistent. Two digit codes can be found [here](https://developers.google.com/admin-sdk/directory/v1/languages) while three digit codes may require further searching.
|
||||||
|
- Models that require BPE preprocessing are not supported.
|
||||||
|
- All model names use the following format: `Helsinki-NLP/opus-mt-{src}-{tgt}`. Language codes formatted like `es_AR` usually refer to the `code_{region}`. For example, `es_AR` refers to Spanish from Argentina.
|
||||||
|
- If a model can output multiple languages, prepend the desired output language to `src_txt` as shown below. New multilingual models from the [Tatoeba-Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge) require 3 character language codes.
|
||||||
|
|
||||||
|
```python
|
||||||
|
|
||||||
|
from transformers import MarianMTModel, MarianTokenizer
|
||||||
|
|
||||||
|
# Model trained on multiple source languages → multiple target languages
|
||||||
|
# Example: multilingual to Arabic (arb)
|
||||||
|
model_name = "Helsinki-NLP/opus-mt-mul-mul" # Tatoeba Challenge model
|
||||||
|
tokenizer = MarianTokenizer.from_pretrained(model_name)
|
||||||
|
model = MarianMTModel.from_pretrained(model_name)
|
||||||
|
|
||||||
|
# Prepend the desired output language code (3-letter ISO 639-3)
|
||||||
|
src_texts = ["arb>> Hello, how are you today?"]
|
||||||
|
|
||||||
|
# Tokenize and translate
|
||||||
|
inputs = tokenizer(src_texts, return_tensors="pt", padding=True, truncation=True)
|
||||||
|
translated = model.generate(**inputs)
|
||||||
|
|
||||||
|
# Decode and print result
|
||||||
|
translated_texts = tokenizer.batch_decode(translated, skip_special_tokens=True)
|
||||||
|
print(translated_texts[0])
|
||||||
|
|
||||||
>>> model = MarianMTModel.from_pretrained(model_name)
|
|
||||||
>>> translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
|
|
||||||
>>> tgt_text = [tokenizer.decode(t, skip_special_tokens=True) for t in translated]
|
|
||||||
["c'est une phrase en anglais que nous voulons traduire en français",
|
|
||||||
'Isto deve ir para o português.',
|
|
||||||
'Y esto al español']
|
|
||||||
```
|
```
|
||||||
|
|
||||||
## Resources
|
- Older multilingual models use 2 character language codes.
|
||||||
|
|
||||||
- [Translation task guide](../tasks/translation)
|
```python
|
||||||
- [Summarization task guide](../tasks/summarization)
|
|
||||||
- [Causal language modeling task guide](../tasks/language_modeling)
|
from transformers import MarianMTModel, MarianTokenizer
|
||||||
|
|
||||||
|
# Example: older multilingual model (like en → many)
|
||||||
|
model_name = "Helsinki-NLP/opus-mt-en-ROMANCE" # English → French, Spanish, Italian, etc.
|
||||||
|
tokenizer = MarianTokenizer.from_pretrained(model_name)
|
||||||
|
model = MarianMTModel.from_pretrained(model_name)
|
||||||
|
|
||||||
|
# Prepend the 2-letter ISO 639-1 target language code (older format)
|
||||||
|
src_texts = [">>fr<< Hello, how are you today?"]
|
||||||
|
|
||||||
|
# Tokenize and translate
|
||||||
|
inputs = tokenizer(src_texts, return_tensors="pt", padding=True, truncation=True)
|
||||||
|
translated = model.generate(**inputs)
|
||||||
|
|
||||||
|
# Decode and print result
|
||||||
|
translated_texts = tokenizer.batch_decode(translated, skip_special_tokens=True)
|
||||||
|
print(translated_texts[0])
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
## MarianConfig
|
## MarianConfig
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user