README.md

---
license: apache-2.0
tags:
- ctranslate2
---
# Fast-Inference with Ctranslate2
Speedup inference by 2x-8x using int8 inference in C++

quantized version of [declare-lab/flan-alpaca-base](https://huggingface.co/declare-lab/flan-alpaca-base)
```bash
pip install hf_hub_ctranslate2>=1.0.0 ctranslate2>=3.13.0
```


Checkpoint compatible to [ctranslate2](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2](https://github.com/michaelfeil/hf-hub-ctranslate2)
- `compute_type=int8_float16` for `device="cuda"` 
- `compute_type=int8`  for `device="cpu"`

```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub

model_name = "michaelfeil/ct2fast-flan-alpaca-base"
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.