Instructions to use ai9stars/AutoTriton with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai9stars/AutoTriton with Transformers:

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

pipe = pipeline("text-generation", model="ai9stars/AutoTriton")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ai9stars/AutoTriton")
model = AutoModelForCausalLM.from_pretrained("ai9stars/AutoTriton")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ai9stars/AutoTriton with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ai9stars/AutoTriton"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai9stars/AutoTriton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ai9stars/AutoTriton

SGLang

How to use ai9stars/AutoTriton 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 "ai9stars/AutoTriton" \
    --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": "ai9stars/AutoTriton",
		"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 "ai9stars/AutoTriton" \
        --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": "ai9stars/AutoTriton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ai9stars/AutoTriton with Docker Model Runner:
```
docker model run hf.co/ai9stars/AutoTriton
```

Improve model card with metadata, paper link, and usage example

by nielsr HF Staff - opened Jul 14, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+64

-2

nielsr

Jul 14, 2025

This PR significantly enhances the model card for AutoTriton. It adds essential metadata such as pipeline_tag (text-generation) and library_name (transformers), making the model more discoverable and properly categorized on the Hugging Face Hub. Additionally, it links the model directly to its corresponding paper and includes relevant tags like code-generation. The card now also features a comprehensive model overview derived from the paper's abstract, details on its evaluation, and a practical transformers usage example.

Improve model card with metadata, paper link, and usage exampleb186c643

LiShangZ

AI9Stars org Aug 1, 2025

Hi @nielsr ，
Sorry for the late reply, and thank you very much for your contribution! 🙏

We reviewed your PR and noticed an issue with the citation.
To address this, we made a revised commit following your structure.

We really appreciate your support and interest in our work!

LiShangZ changed pull request status to closed Aug 1, 2025

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