michaelfeil / ct2fast-flan-ul2

huggingface.co
Total runs: 16
24-hour runs: 0
7-day runs: 3
30-day runs: 6
Model's Last Updated: May 19 2023

Introduction of ct2fast-flan-ul2

Model Details of ct2fast-flan-ul2

Fast-Inference with Ctranslate2

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

quantized version of google/flan-ul2

pip install hf_hub_ctranslate2>=2.0.6 ctranslate2>=3.13.0

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

model_name = "michaelfeil/ct2fast-flan-ul2"
model = TranslatorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        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?"],
    min_decoding_length=24,
    max_decoding_length=32,
    max_input_length=512,
    beam_size=5
)
print(outputs)

Licence and other remarks:

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

Runs of michaelfeil ct2fast-flan-ul2 on huggingface.co

16
Total runs
0
24-hour runs
3
3-day runs
3
7-day runs
6
30-day runs

More Information About ct2fast-flan-ul2 huggingface.co Model

More ct2fast-flan-ul2 license Visit here:

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

ct2fast-flan-ul2 huggingface.co

ct2fast-flan-ul2 huggingface.co is an AI model on huggingface.co that provides ct2fast-flan-ul2's model effect (), which can be used instantly with this michaelfeil ct2fast-flan-ul2 model. huggingface.co supports a free trial of the ct2fast-flan-ul2 model, and also provides paid use of the ct2fast-flan-ul2. Support call ct2fast-flan-ul2 model through api, including Node.js, Python, http.

michaelfeil ct2fast-flan-ul2 online free

ct2fast-flan-ul2 huggingface.co is an online trial and call api platform, which integrates ct2fast-flan-ul2's modeling effects, including api services, and provides a free online trial of ct2fast-flan-ul2, you can try ct2fast-flan-ul2 online for free by clicking the link below.

michaelfeil ct2fast-flan-ul2 online free url in huggingface.co:

https://huggingface.co/michaelfeil/ct2fast-flan-ul2

ct2fast-flan-ul2 install

ct2fast-flan-ul2 is an open source model from GitHub that offers a free installation service, and any user can find ct2fast-flan-ul2 on GitHub to install. At the same time, huggingface.co provides the effect of ct2fast-flan-ul2 install, users can directly use ct2fast-flan-ul2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

ct2fast-flan-ul2 install url in huggingface.co:

https://huggingface.co/michaelfeil/ct2fast-flan-ul2

Url of ct2fast-flan-ul2

ct2fast-flan-ul2 huggingface.co Url

Provider of ct2fast-flan-ul2 huggingface.co

michaelfeil
ORGANIZATIONS

Other API from michaelfeil