Instructions to use ZonglinY/MOOSE-Star-IR-R1D-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZonglinY/MOOSE-Star-IR-R1D-7B with Transformers:

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

pipe = pipeline("text-generation", model="ZonglinY/MOOSE-Star-IR-R1D-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZonglinY/MOOSE-Star-IR-R1D-7B")
model = AutoModelForCausalLM.from_pretrained("ZonglinY/MOOSE-Star-IR-R1D-7B")
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 Settings

vLLM

How to use ZonglinY/MOOSE-Star-IR-R1D-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZonglinY/MOOSE-Star-IR-R1D-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZonglinY/MOOSE-Star-IR-R1D-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ZonglinY/MOOSE-Star-IR-R1D-7B

SGLang

How to use ZonglinY/MOOSE-Star-IR-R1D-7B 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 "ZonglinY/MOOSE-Star-IR-R1D-7B" \
    --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": "ZonglinY/MOOSE-Star-IR-R1D-7B",
		"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 "ZonglinY/MOOSE-Star-IR-R1D-7B" \
        --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": "ZonglinY/MOOSE-Star-IR-R1D-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ZonglinY/MOOSE-Star-IR-R1D-7B with Docker Model Runner:
```
docker model run hf.co/ZonglinY/MOOSE-Star-IR-R1D-7B
```

Add library_name metadata and improve repository links

by nielsr HF Staff - opened Mar 7

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+22

-12

nielsr

Mar 7

Hi! I'm Niels from the community science team at Hugging Face.

This pull request improves the model card for MOOSE-Star-IR-R1D-7B by:

Adding the library_name: transformers metadata tag to enable automated code snippets and the "Use in Transformers" button on the hub.
Adding explicit links to the original paper and the GitHub repository for better discoverability.

The content remains focused on the technical implementation, maintaining the detailed task descriptions and usage examples you provided.

Add library_name metadata and improve repository links59f32065

ZonglinY changed pull request status to merged Mar 9

ZonglinY

Owner Mar 9

Thanks for the improvement, Niels! Merged.

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