Instructions to use UCSC-VLAA/STAR1-R1-Distill-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UCSC-VLAA/STAR1-R1-Distill-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="UCSC-VLAA/STAR1-R1-Distill-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UCSC-VLAA/STAR1-R1-Distill-1.5B")
model = AutoModelForCausalLM.from_pretrained("UCSC-VLAA/STAR1-R1-Distill-1.5B")
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]:]))

Inference
Local Apps Settings

vLLM

How to use UCSC-VLAA/STAR1-R1-Distill-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UCSC-VLAA/STAR1-R1-Distill-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UCSC-VLAA/STAR1-R1-Distill-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UCSC-VLAA/STAR1-R1-Distill-1.5B

SGLang

How to use UCSC-VLAA/STAR1-R1-Distill-1.5B 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 "UCSC-VLAA/STAR1-R1-Distill-1.5B" \
    --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": "UCSC-VLAA/STAR1-R1-Distill-1.5B",
		"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 "UCSC-VLAA/STAR1-R1-Distill-1.5B" \
        --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": "UCSC-VLAA/STAR1-R1-Distill-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use UCSC-VLAA/STAR1-R1-Distill-1.5B with Docker Model Runner:
```
docker model run hf.co/UCSC-VLAA/STAR1-R1-Distill-1.5B
```

Populate Model Card for STAR-1

by nielsr HF Staff - opened Apr 3, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+47

-133

nielsr

Apr 3, 2025

This PR populates the automatically generated model card with details from the provided information. It adds the license, pipeline tag, links to the project page and GitHub repository, and a brief model description. Further details about the model, its uses, biases, and training specifics should be added as more information becomes available. Please update with the appropriate license if it differs from Apache-2.0.

Populate Model Card for STAR-1fe2c816b

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

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md

· Sign up or log in to comment