Instructions to use universalml/NepaliGPT-2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use universalml/NepaliGPT-2.0 with Transformers:

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

pipe = pipeline("text-generation", model="universalml/NepaliGPT-2.0")
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("universalml/NepaliGPT-2.0")
model = AutoModelForCausalLM.from_pretrained("universalml/NepaliGPT-2.0", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use universalml/NepaliGPT-2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "universalml/NepaliGPT-2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "universalml/NepaliGPT-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/universalml/NepaliGPT-2.0

SGLang

How to use universalml/NepaliGPT-2.0 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 "universalml/NepaliGPT-2.0" \
    --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": "universalml/NepaliGPT-2.0",
		"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 "universalml/NepaliGPT-2.0" \
        --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": "universalml/NepaliGPT-2.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use universalml/NepaliGPT-2.0 with Docker Model Runner:
```
docker model run hf.co/universalml/NepaliGPT-2.0
```

Collaboration

by Supernova11c - opened 7 days ago

Discussion

Supernova11c

7 days ago

Dear Team,

Greetings from Supernova!

We are reaching out to explore a potential technical and research collaboration with your organization.

Supernova is an independent, student-founded technology and research initiative based in Nepal. Our founding team consists of school students, and our goal is to contribute to Nepal's technology ecosystem by developing original software, AI systems, research projects, and computing technologies.

Our ongoing and experimental projects include:

TeraiLLM: A Nepali-first language-model research project.
Supernova Tokenizer V5: A Nepali-focused tokenizer with Unicode support and benchmark testing.
TeraiTTS and TeraiASR: Nepali text-to-speech and speech-recognition research.
Supernova Catalyst DB: A Rust-based database-engine project.
Shiva Shakti SS64: An experimental processor and custom instruction-set project.
PHOTON-1: An experimental scientific and computational project.

We are particularly interested in exploring opportunities for:

Technical mentorship and engineering guidance.
Research collaboration and knowledge exchange.
Computing resources or infrastructure support, where possible.
Joint experimentation, testing, and evaluation.
Long-term collaboration on projects that align with both organizations' interests.

Supernova intends to remain an independent initiative while fairly acknowledging the contributions of any collaborating organization. We are open to discussing a suitable collaboration model based on mutual interests and capabilities.

We would appreciate the opportunity to introduce our work and discuss whether there may be a suitable way to collaborate.

Our links:

Website: https://little-entire-prediction--supernova11c.replit.app/

Hugging Face: https://huggingface.co/Supernova11c

We are happy to share further technical information and arrange a short introductory meeting.

Thank you for your time and consideration. We would appreciate hearing whether this opportunity is relevant to your team and, if possible, your expected response timeline.

Best regards,

Supernova Team
Independent Student-Led Technology Initiative
Nepal
Email: supernova11c.np@gmail.com

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment