Instructions to use Emeritus-21/yorubanumerals-expertsystem with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Emeritus-21/yorubanumerals-expertsystem with Transformers:

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

pipe = pipeline("text-generation", model="Emeritus-21/yorubanumerals-expertsystem")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Emeritus-21/yorubanumerals-expertsystem")
model = AutoModelForSeq2SeqLM.from_pretrained("Emeritus-21/yorubanumerals-expertsystem")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Emeritus-21/yorubanumerals-expertsystem with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Emeritus-21/yorubanumerals-expertsystem"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Emeritus-21/yorubanumerals-expertsystem",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Emeritus-21/yorubanumerals-expertsystem

SGLang

How to use Emeritus-21/yorubanumerals-expertsystem 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 "Emeritus-21/yorubanumerals-expertsystem" \
    --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": "Emeritus-21/yorubanumerals-expertsystem",
		"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 "Emeritus-21/yorubanumerals-expertsystem" \
        --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": "Emeritus-21/yorubanumerals-expertsystem",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Emeritus-21/yorubanumerals-expertsystem with Docker Model Runner:
```
docker model run hf.co/Emeritus-21/yorubanumerals-expertsystem
```

yorubanumerals-expertsystem / README.md

Emeritus-21

Update README.md

c95b8cb verified 11 months ago

preview code

raw

history blame contribute delete

827 Bytes

metadata

tags:
  - text2text-generation
  - roman-numerals
  - yoruba
  - byt5
license: apache-2.0
library_name: transformers
pipeline_tag: text2text-generation
model_type: encoder-decoder
base_model: google/byt5-small

Yoruba Roman Numerals Expert System 🇳🇬🔢

This model is fine-tuned from google/byt5-small to translate Roman numerals (e.g. 'i','v','x','XIV, V̅M, up to 6000) into Yoruba text.

Example Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Emeritus-21/yorubanumerals-expertsystem")
model = AutoModelForSeq2SeqLM.from_pretrained("Emeritus-21/yorubanumerals-expertsystem")

inputs = tokenizer("V̅M", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))