michaelfeil / ct2fast-opus-mt-es-en

huggingface.co
Total runs: 18
24-hour runs: 0
7-day runs: 14
30-day runs: 12
Model's Last Updated: May 19 2023
translation

Introduction of ct2fast-opus-mt-es-en

Model Details of ct2fast-opus-mt-es-en

# Fast-Inference with Ctranslate2

Speedup inference by 2x-8x using int8 inference in C++

quantized version of Helsinki-NLP/opus-mt-es-en

pip install hf-hub-ctranslate2>=1.0.0 ctranslate2>=3.13.0

Converted using

ct2-transformers-converter --model Helsinki-NLP/opus-mt-es-en --output_dir /home/michael/tmp-ct2fast-opus-mt-es-en --force --copy_files README.md generation_config.json tokenizer_config.json vocab.json source.spm .gitattributes target.spm --quantization float16

Checkpoint compatible to ctranslate2 and hf-hub-ctranslate2

  • compute_type=int8_float16 for device="cuda"
  • compute_type=int8 for device="cpu"
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer

model_name = "michaelfeil/ct2fast-opus-mt-es-en"
# use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
model = TranslatorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        device="cuda",
        compute_type="int8_float16",
        tokenizer=AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-es-en")
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "User: How are you doing?"],
)
print(outputs)

Licence and other remarks:

This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

Original description

spa-eng
Benchmarks
testset BLEU chr-F
newssyscomb2009-spaeng.spa.eng 30.6 0.570
news-test2008-spaeng.spa.eng 27.9 0.553
newstest2009-spaeng.spa.eng 30.4 0.572
newstest2010-spaeng.spa.eng 36.1 0.614
newstest2011-spaeng.spa.eng 34.2 0.599
newstest2012-spaeng.spa.eng 37.9 0.624
newstest2013-spaeng.spa.eng 35.3 0.609
Tatoeba-test.spa.eng 59.6 0.739
System Info:

Runs of michaelfeil ct2fast-opus-mt-es-en on huggingface.co

18
Total runs
0
24-hour runs
11
3-day runs
14
7-day runs
12
30-day runs

More Information About ct2fast-opus-mt-es-en huggingface.co Model

More ct2fast-opus-mt-es-en license Visit here:

https://choosealicense.com/licenses/apache-2.0

ct2fast-opus-mt-es-en huggingface.co

ct2fast-opus-mt-es-en huggingface.co is an AI model on huggingface.co that provides ct2fast-opus-mt-es-en's model effect (), which can be used instantly with this michaelfeil ct2fast-opus-mt-es-en model. huggingface.co supports a free trial of the ct2fast-opus-mt-es-en model, and also provides paid use of the ct2fast-opus-mt-es-en. Support call ct2fast-opus-mt-es-en model through api, including Node.js, Python, http.

ct2fast-opus-mt-es-en huggingface.co Url

https://huggingface.co/michaelfeil/ct2fast-opus-mt-es-en

michaelfeil ct2fast-opus-mt-es-en online free

ct2fast-opus-mt-es-en huggingface.co is an online trial and call api platform, which integrates ct2fast-opus-mt-es-en's modeling effects, including api services, and provides a free online trial of ct2fast-opus-mt-es-en, you can try ct2fast-opus-mt-es-en online for free by clicking the link below.

michaelfeil ct2fast-opus-mt-es-en online free url in huggingface.co:

https://huggingface.co/michaelfeil/ct2fast-opus-mt-es-en

ct2fast-opus-mt-es-en install

ct2fast-opus-mt-es-en is an open source model from GitHub that offers a free installation service, and any user can find ct2fast-opus-mt-es-en on GitHub to install. At the same time, huggingface.co provides the effect of ct2fast-opus-mt-es-en install, users can directly use ct2fast-opus-mt-es-en installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

ct2fast-opus-mt-es-en install url in huggingface.co:

https://huggingface.co/michaelfeil/ct2fast-opus-mt-es-en

Url of ct2fast-opus-mt-es-en

ct2fast-opus-mt-es-en huggingface.co Url

Provider of ct2fast-opus-mt-es-en huggingface.co

michaelfeil
ORGANIZATIONS

Other API from michaelfeil