Instructions to use manavdhamecha77/GEC-mT5-Small-Tamil with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use manavdhamecha77/GEC-mT5-Small-Tamil with Transformers:

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

pipe = pipeline("text-generation", model="manavdhamecha77/GEC-mT5-Small-Tamil")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("manavdhamecha77/GEC-mT5-Small-Tamil")
model = AutoModelForMultimodalLM.from_pretrained("manavdhamecha77/GEC-mT5-Small-Tamil")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use manavdhamecha77/GEC-mT5-Small-Tamil with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "manavdhamecha77/GEC-mT5-Small-Tamil"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "manavdhamecha77/GEC-mT5-Small-Tamil",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/manavdhamecha77/GEC-mT5-Small-Tamil

SGLang

How to use manavdhamecha77/GEC-mT5-Small-Tamil 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 "manavdhamecha77/GEC-mT5-Small-Tamil" \
    --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": "manavdhamecha77/GEC-mT5-Small-Tamil",
		"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 "manavdhamecha77/GEC-mT5-Small-Tamil" \
        --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": "manavdhamecha77/GEC-mT5-Small-Tamil",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use manavdhamecha77/GEC-mT5-Small-Tamil with Docker Model Runner:
```
docker model run hf.co/manavdhamecha77/GEC-mT5-Small-Tamil
```

manavdhamecha77 commited on Mar 14

Commit

5bdf296

verified ·

1 Parent(s): 634c83f

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ A multilingual Grammatical Error Correction (GEC) model fine-tuned from [mT5-sma
 - **Base model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
 - **Paper:** [Team Horizon at BHASHA Task 1](https://aclanthology.org/2025.bhasha-1.14/)
 - **Repository:** [manavdhamecha77/IndicGEC2025](https://github.com/manavdhamecha77/IndicGEC2025)
-- **GitHub.io:** [Indic Word Grouping](https://manavdhamecha77.github.io/wg/)
 ---

 - **Base model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
 - **Paper:** [Team Horizon at BHASHA Task 1](https://aclanthology.org/2025.bhasha-1.14/)
 - **Repository:** [manavdhamecha77/IndicGEC2025](https://github.com/manavdhamecha77/IndicGEC2025)
+- **GitHub.io:** [Multilingual IndicGEC](https://manavdhamecha77.github.io/gec/)
 ---