Instructions to use atsuki-yamaguchi/bloom-7b1-random-ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use atsuki-yamaguchi/bloom-7b1-random-ar with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="atsuki-yamaguchi/bloom-7b1-random-ar")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("atsuki-yamaguchi/bloom-7b1-random-ar")
model = AutoModelForCausalLM.from_pretrained("atsuki-yamaguchi/bloom-7b1-random-ar")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use atsuki-yamaguchi/bloom-7b1-random-ar with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "atsuki-yamaguchi/bloom-7b1-random-ar"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atsuki-yamaguchi/bloom-7b1-random-ar",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/atsuki-yamaguchi/bloom-7b1-random-ar

SGLang

How to use atsuki-yamaguchi/bloom-7b1-random-ar with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "atsuki-yamaguchi/bloom-7b1-random-ar" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atsuki-yamaguchi/bloom-7b1-random-ar",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "atsuki-yamaguchi/bloom-7b1-random-ar" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "atsuki-yamaguchi/bloom-7b1-random-ar",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use atsuki-yamaguchi/bloom-7b1-random-ar with Docker Model Runner:
```
docker model run hf.co/atsuki-yamaguchi/bloom-7b1-random-ar
```

BLOOM-7B Arabic [LAPT + Random]

How to use

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer

model = AutoPeftModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/bloom-7b1-random-ar"
)
tokenizer = AutoTokenizer.from_pretrained(
    "aubmindlab/aragpt2-base"
)

# w/ GPU
model = AutoPeftModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/bloom-7b1-random-ar",
    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

Downloads last month: 5

Safetensors

Model size

6B params

Tensor type

F64

F32

Collection including atsuki-yamaguchi/bloom-7b1-random-ar

Cross-lingual Vocabulary Adaptation for Inference Speeups

Collection

Collection of models for "An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference" (EMNLP Findings 2024) • 113 items • Updated Nov 3, 2025

Paper for atsuki-yamaguchi/bloom-7b1-random-ar

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative LLM Inference

Paper • 2402.10712 • Published Feb 16, 2024