Instructions to use vinothkannans/hello-world with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vinothkannans/hello-world with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vinothkannans/hello-world")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vinothkannans/hello-world", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use vinothkannans/hello-world with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vinothkannans/hello-world" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vinothkannans/hello-world", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vinothkannans/hello-world
- SGLang
How to use vinothkannans/hello-world 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 "vinothkannans/hello-world" \ --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": "vinothkannans/hello-world", "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 "vinothkannans/hello-world" \ --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": "vinothkannans/hello-world", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vinothkannans/hello-world with Docker Model Runner:
docker model run hf.co/vinothkannans/hello-world
Hello World AI Model
A simple demonstration model built with Hugging Face Transformers that always returns "Hello World". This model serves as a minimal example of creating custom models using the Transformers library.
Model Description
The Hello World AI Model is a custom PyTorch model that extends PreTrainedModel from the Hugging Face Transformers library. It's designed as a learning example and template for building custom models.
- Developed by: Vinoth Kannan
- Model type: Custom PyTorch Model
- Language(s): English
- License: MIT
Model Details
Model Architecture
The model consists of:
- A single linear layer (
nn.Linear(1, 1)) for demonstration purposes - A forward method that returns
{"text": "Hello World"}regardless of input
Training
This is a demonstration model and does not require training. It's a static model that always returns the same output.
Usage
Using Transformers
from transformers import AutoModel, AutoConfig
# Load the model
model = AutoModel.from_pretrained("vinothkannans/hello-world")
config = AutoConfig.from_pretrained("vinothkannans/hello-world")
# Use the model
output = model.forward()
print(output) # {'text': 'Hello World'}
Using PyTorch
import torch
from transformers import AutoModel
model = AutoModel.from_pretrained("vinothkannans/hello-world")
model.eval()
with torch.no_grad():
output = model.forward()
print(output) # {'text': 'Hello World'}
Model Card Contact
For questions or issues, please contact vinothkannans on Hugging Face.
Limitations
This is a demonstration model for the learing production purposes. It always returns the same output regardless of input.
Citation
@misc{hello-world-model,
author = {Vinoth Kannan},
title = {Hello World AI Model},
year = {2025},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/vinothkannans/hello-world}}
}
License
This model is licensed under the MIT License. See the LICENSE file for more details.
- Downloads last month
- -