Instructions to use TidasSilva/SinghaGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TidasSilva/SinghaGPT with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TidasSilva/SinghaGPT")
model = AutoModelForCausalLM.from_pretrained("TidasSilva/SinghaGPT", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TidasSilva/SinghaGPT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TidasSilva/SinghaGPT

SGLang

How to use TidasSilva/SinghaGPT 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 "TidasSilva/SinghaGPT" \
    --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": "TidasSilva/SinghaGPT",
		"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 "TidasSilva/SinghaGPT" \
        --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": "TidasSilva/SinghaGPT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TidasSilva/SinghaGPT with Docker Model Runner:
```
docker model run hf.co/TidasSilva/SinghaGPT
```

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Singha GPT 1.2

Singha GPT is a multilingual model project focused on Sri Lankan history, culture, heritage and languages.

Foundation

Base model: Qwen/Qwen3-4B
Fine-tuning: LoRA adapter merged into foundation weights
Model format: Safetensors
Model architecture: Qwen3ForCausalLM

Loading

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

repo = "YOUR_USERNAME/singha-gpt-1.2"

tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    torch_dtype=torch.float16,
    device_map="auto"
)

Evaluation

The repository includes an initial five-question inference smoke-test report. This is not a comprehensive factual accuracy benchmark.

Licensing

This model is based on Qwen3-4B. Review the original foundation-model licence and the provenance and licences of all fine-tuning datasets before redistribution.

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

BF16