Instructions to use l3cube-pune/IndicGuard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use l3cube-pune/IndicGuard with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-4b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "l3cube-pune/IndicGuard")

Transformers

How to use l3cube-pune/IndicGuard with Transformers:

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

pipe = pipeline("text-generation", model="l3cube-pune/IndicGuard")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("l3cube-pune/IndicGuard", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use l3cube-pune/IndicGuard with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "l3cube-pune/IndicGuard"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3cube-pune/IndicGuard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/l3cube-pune/IndicGuard

SGLang

How to use l3cube-pune/IndicGuard 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 "l3cube-pune/IndicGuard" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3cube-pune/IndicGuard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "l3cube-pune/IndicGuard" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3cube-pune/IndicGuard",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use l3cube-pune/IndicGuard with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for l3cube-pune/IndicGuard to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for l3cube-pune/IndicGuard to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for l3cube-pune/IndicGuard to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="l3cube-pune/IndicGuard",
    max_seq_length=2048,
)

Docker Model Runner
How to use l3cube-pune/IndicGuard with Docker Model Runner:
```
docker model run hf.co/l3cube-pune/IndicGuard
```

l3cube-pune commited on 18 days ago

Commit

ff4cc5d

verified ·

1 Parent(s): 4f33f00

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -42,7 +42,7 @@ IndicGuard supports **10 Indic languages**: Hindi, Marathi, Bengali, Tamil, Telu
 - **Base model:** `unsloth/gemma-3-4b-it-unsloth-bnb-4bit`
 - **Languages:** Hindi (`hi`), Marathi (`mr`), Bengali (`bn`), Tamil (`ta`), Telugu (`te`), Kannada (`kn`), Malayalam (`ml`), Gujarati (`gu`), Punjabi (`pa`), Odia (`or`)
 - **License:** apache-2.0
-- **Paper:** [More Information Needed]
 ---

 - **Base model:** `unsloth/gemma-3-4b-it-unsloth-bnb-4bit`
 - **Languages:** Hindi (`hi`), Marathi (`mr`), Bengali (`bn`), Tamil (`ta`), Telugu (`te`), Kannada (`kn`), Malayalam (`ml`), Gujarati (`gu`), Punjabi (`pa`), Odia (`or`)
 - **License:** apache-2.0
+- **Paper:** [IndicGuard](https://arxiv.org/abs/2606.22841)
 ---