An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative LLM Inference
Paper • 2402.10712 • Published
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
bloom-1b1-focus-sw - bnb 8bits
- Model creator: https://huggingface.co/atsuki-yamaguchi/
- Original model: https://huggingface.co/atsuki-yamaguchi/bloom-1b1-focus-sw/
Original model description:
license: mit language: sw
BLOOM-1B Swahili [LAPT + FOCUS]
How to use
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
model = AutoPeftModelForCausalLM.from_pretrained(
"atsuki-yamaguchi/bloom-1b1-focus-sw"
)
tokenizer = AutoTokenizer.from_pretrained(
"atsuki-yamaguchi/bloom-1b1-focus-sw"
)
# w/ GPU
model = AutoPeftModelForCausalLM.from_pretrained(
"atsuki-yamaguchi/bloom-1b1-focus-sw",
device_map="auto",
load_in_8bit=True,
)
Citation
@article{yamaguchi2024empirical,
title={An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative {LLM} Inference},
author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
journal={ArXiv},
year={2024},
volume={abs/2402.10712},
url={https://arxiv.org/abs/2402.10712}
}
Link
For more details, please visit https://github.com/gucci-j/llm-cva
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support