Instructions to use lm-spell/mt5-base-ft-ssc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lm-spell/mt5-base-ft-ssc with Transformers:

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

pipe = pipeline("text-generation", model="lm-spell/mt5-base-ft-ssc")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("lm-spell/mt5-base-ft-ssc")
model = AutoModelForSeq2SeqLM.from_pretrained("lm-spell/mt5-base-ft-ssc", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lm-spell/mt5-base-ft-ssc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lm-spell/mt5-base-ft-ssc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lm-spell/mt5-base-ft-ssc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lm-spell/mt5-base-ft-ssc

SGLang

How to use lm-spell/mt5-base-ft-ssc 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 "lm-spell/mt5-base-ft-ssc" \
    --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": "lm-spell/mt5-base-ft-ssc",
		"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 "lm-spell/mt5-base-ft-ssc" \
        --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": "lm-spell/mt5-base-ft-ssc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lm-spell/mt5-base-ft-ssc with Docker Model Runner:
```
docker model run hf.co/lm-spell/mt5-base-ft-ssc
```

mt5-base-ft-ssc / README.md

AkeshSamuditha

Upload README.md with huggingface_hub

037ad42 verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

814 Bytes

	---
	tags:
	- text-generation
	- fine-tuned
	- mt5
	- spell-correction
	license: cc-by-4.0
	library_name: transformers
	language: si
	model_type: mt5
	finetuned_from: google/mt5-base
	datasets:
	- lm-spell/sinhala-spell-correction-dataset
	---

	# mt5-base-ft-ssc

	## Model Details
	# - Developed by: Team Surgical Masks
	- License: cc-by-4.0
	- Model type: mt5
	- Language(s) (NLP): si
	- Fine-tuned from: [google/mt5-base](https://huggingface.co/google/mt5-base)
	- Dataset Used: [lm-spell/sinhala-spell-correction-dataset](https://huggingface.co/datasets/lm-spell/sinhala-spell-correction-dataset)

	## Model Sources
	- Repository: [Not Provided]
	# - Paper: [Not Provided]

	## Model Description
	This model is a fine-tuned version of google/mt5-base for Sinhala Spell Correction.