michaelfeil / ct2fast-opus-mt-en-ROMANCE

huggingface.co
Total runs: 8
24-hour runs: 0
7-day runs: 0
30-day runs: 2
Model's Last Updated: May 19 2023
translation

Introduction of ct2fast-opus-mt-en-ROMANCE

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

# Fast-Inference with Ctranslate2

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

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

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

Converted using

ct2-transformers-converter --model Helsinki-NLP/opus-mt-en-ROMANCE --output_dir /home/michael/tmp-ct2fast-opus-mt-en-ROMANCE --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-en-ROMANCE"
# 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-en-ROMANCE")
)
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

opus-mt-en-ROMANCE
Benchmarks
testset BLEU chr-F
Tatoeba.en.la 50.1 0.693

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

8
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
2
30-day runs

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

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

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

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

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

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

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

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

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

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

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

ct2fast-opus-mt-en-ROMANCE install

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

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

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

Url of ct2fast-opus-mt-en-ROMANCE

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

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

michaelfeil
ORGANIZATIONS

Other API from michaelfeil