hf_hub_ctranslate2
Connecting Transformers on HuggingfaceHub with Ctranslate2 - a small utility for keeping tokenizer and model around Huggingface Hub.
Usage:
PYPI Install
pip install hf-hub-ctranslate2
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:
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub
# 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):
from hf_hub_ctranslate2 import MultiLingualTranslatorCT2fromHfHub
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"]
)
Encoder-only Sentence Transformers
Feel free to try out a new repo, using CTranslate2 for vector-embeddings: https://github.com/michaelfeil/infinity
from hf_hub_ctranslate2 import CT2SentenceTransformer
model_name_pytorch = "intfloat/e5-small"
model = CT2SentenceTransformer(
model_name_pytorch, compute_type="int8", device="cuda",
)
embeddings = model.encode(
["I like soccer", "I like tennis", "The eiffel tower is in Paris"],
batch_size=32,
convert_to_numpy=True,
normalize_embeddings=True,
)
print(embeddings.shape, embeddings)
scores = (embeddings @ embeddings.T) * 100
Encoder-only -> no longer recommended
from hf_hub_ctranslate2 import EncoderCT2fromHfHub
model_name = "michaelfeil/ct2fast-e5-small"
model = EncoderCT2fromHfHub(
# load in int8 on CUDA
model_name_or_path=model_name,
device="cuda",
compute_type="int8_float16",
)
outputs = model.generate(
text=["I like soccer", "I like tennis", "The eiffel tower is in Paris"],
max_length=64,
)
Metadata
Release files for hf-hub-ctranslate2 2.13.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| hf_hub_ctranslate2-2.13.1.tar.gz | 10.0 kB | Without provenance | Details for hf_hub_ctranslate2-2.13.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| hf_hub_ctranslate2-2.13.1-py3-none-any.whl | Python 3 | none | any | Details for hf_hub_ctranslate2-2.13.1-py3-none-any.whl |
Total release size: 20.6 kB
Release files / hf_hub_ctranslate2-2.13.1.tar.gz
| Download URL | hf_hub_ctranslate2-2.13.1.tar.gz |
|---|---|
| Size | 10.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e3d41d859fdea39a745a1ae4f754f24c124d9d96b0dd415317ee71141042faee
|
|
BLAKE2b-256 checksum How to use checksums |
b9bb2f1850ca94b95dee5bb0221d85d93c99196a8452e40b354b0d9562ecb4ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/5.1.0 CPython/3.12.4
|
Release files / hf_hub_ctranslate2-2.13.1-py3-none-any.whl
| Download URL | hf_hub_ctranslate2-2.13.1-py3-none-any.whl |
|---|---|
| Size | 10.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
389ed6102f18d3a84cb466bddd07e1e5e532bc91ddc47d3639c9eb11cdd43a86
|
|
BLAKE2b-256 checksum How to use checksums |
a73c24980d9f448fc04e7f6371499d6cf29919238c7566f34000604074351e89
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/5.1.0 CPython/3.12.4
|
Security for hf-hub-ctranslate2 2.13.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.