hf-hub-ctranslate2 2.0.5

Connecting Transfromers on HuggingfaceHub with Ctranslate2

hf_hub_ctranslate2

Connecting Transfromers on HuggingfaceHub with Ctranslate2 - a small utility for keeping tokenizer and model around Huggingface Hub.

Read the docs

---

Usage:

Decoder-only Transformer:

# download ctranslate.Generator repos from Huggingface Hub (GPT-J, ..)
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub

model_name_1="michaelfeil/ct2fast-pythia-160m"
model = GeneratorCT2fromHfHub(
    # load in int8 on CPU
    model_name_or_path=model_name_1, device="cpu", compute_type="int8"
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "User: How are you doing?"]
    # add arguments specifically to ctranslate2.Generator here
)

Encoder-Decoder:

# download ctranslate.Translator repos from Huggingface Hub (T5, ..)
model_name_2 = "michaelfeil/ct2fast-flan-alpaca-base"
model = TranslatorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name_2, device="cuda", compute_type="int8_float16"
)
outputs = model.generate(
    text=["How do you call a fast Flan-ingo?", "Translate to german: How are you doing?"],
    # use arguments specifically to ctranslate2.Translator below:
    min_decoding_length=8,
    max_decoding_length=16,
    max_input_length=512,
    beam_size=3
)
print(outputs)

Encoder-Decoder for multilingual translations (m2m-100):

model = MultiLingualTranslatorCT2fromHfHub(
    model_name_or_path="michaelfeil/ct2fast-m2m100_418M", device="cpu", compute_type="int8",
    tokenizer=AutoTokenizer.from_pretrained(f"facebook/m2m100_418M")
)

outputs = model.generate(
    ["How do you call a fast Flamingo?", "Wie geht es dir?"],
    src_lang=["en", "de"],
    tgt_lang=["de", "fr"]
)

---

PYPI Install

pip install hf-hub-ctranslate2

---