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

Libraries

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

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

pipe = pipeline("text-generation", model="ZonglinY/MOOSE-Star-HC-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-HC-R1D-7B")
model = AutoModelForCausalLM.from_pretrained("ZonglinY/MOOSE-Star-HC-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

vLLM

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

Use Docker

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

SGLang

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

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

MOOSE-Star-HC-R1D-7B

Commit History

Add copy-paste IR/HC prompt examples (TOMATO-Star Oct 2025 test case)

765acee
verified

ZonglinY commited on 13 days ago

Embed chat_template into tokenizer_config.json for vLLM/inference-provider compatibility

1d564cd
verified

ZonglinY commited on 13 days ago

Upload README.md with huggingface_hub

4157ec7
verified

ZonglinY commited on Apr 4

Upload README.md with huggingface_hub

563db59
verified

ZonglinY commited on Apr 4

Upload README.md with huggingface_hub

b3330af
verified

ZonglinY commited on Apr 4

Upload README.md with huggingface_hub

58f33b2
verified

ZonglinY commited on Apr 4

Upload README.md with huggingface_hub

0175ad2
verified

ZonglinY commited on Apr 4

Upload README.md with huggingface_hub

1e7b662
verified

ZonglinY commited on Apr 4

Add library_name metadata and link to code (#1)

888e017

ZonglinY

nielsr HF Staff commited on Mar 9

Update arxiv link to 2603.03756

8c73782
verified

ZonglinY commited on Mar 5

Fix prompt format: unify to delta output format, remove incorrect normal composition section

e6689d6
verified

ZonglinY commited on Mar 4

Update model card: fix epochs (1), usage code (prompt_store.py, dtype=auto, add_generation_prompt=False), output format, add full prompt details block

afcec2b
verified

ZonglinY commited on Mar 4

Update README: add prompt format, fix eval numbers, update cross-references

5a17351
verified

ZonglinY commited on Mar 3

Update README with new repo/model names

b60838e
verified

ZonglinY commited on Mar 3

Add chat_template.jinja

019c8bb
verified

ZonglinY commited on Mar 2

Add tokenizer_config.json

6b10642
verified

ZonglinY commited on Mar 2

Add tokenizer.json

35b57f3
verified

ZonglinY commited on Mar 2

Add special_tokens_map.json

3b56ab6
verified

ZonglinY commited on Mar 2

Add model.safetensors.index.json

84600f7
verified

ZonglinY commited on Mar 2

Add model-00004-of-00004.safetensors

3490ef9
verified

ZonglinY commited on Mar 2

Add model-00003-of-00004.safetensors

eb37a38
verified

ZonglinY commited on Mar 2

Add model-00002-of-00004.safetensors

87109a4
verified

ZonglinY commited on Mar 2

Add model-00001-of-00004.safetensors

4dc8bc1
verified

ZonglinY commited on Mar 2

Add generation_config.json

8fa9f84
verified

ZonglinY commited on Mar 2

Add config.json

ca8aa3d
verified

ZonglinY commited on Mar 2

Add Model Card

3101968
verified

ZonglinY commited on Mar 2

initial commit

53095a8
verified

ZonglinY commited on Mar 2

Commit History

Add copy-paste IR/HC prompt examples (TOMATO-Star Oct 2025 test case) 765acee verified

Embed chat_template into tokenizer_config.json for vLLM/inference-provider compatibility 1d564cd verified

Upload README.md with huggingface_hub 4157ec7 verified

Upload README.md with huggingface_hub 563db59 verified

Upload README.md with huggingface_hub b3330af verified

Upload README.md with huggingface_hub 58f33b2 verified

Upload README.md with huggingface_hub 0175ad2 verified

Upload README.md with huggingface_hub 1e7b662 verified

Add library_name metadata and link to code (#1) 888e017

Update arxiv link to 2603.03756 8c73782 verified

Fix prompt format: unify to delta output format, remove incorrect normal composition section e6689d6 verified

Update model card: fix epochs (1), usage code (prompt_store.py, dtype=auto, add_generation_prompt=False), output format, add full prompt details block afcec2b verified

Update README: add prompt format, fix eval numbers, update cross-references 5a17351 verified

Update README with new repo/model names b60838e verified

Add chat_template.jinja 019c8bb verified

Add tokenizer_config.json 6b10642 verified

Add tokenizer.json 35b57f3 verified

Add special_tokens_map.json 3b56ab6 verified

Add model.safetensors.index.json 84600f7 verified

Add model-00004-of-00004.safetensors 3490ef9 verified

Add model-00003-of-00004.safetensors eb37a38 verified

Add model-00002-of-00004.safetensors 87109a4 verified

Add model-00001-of-00004.safetensors 4dc8bc1 verified

Add generation_config.json 8fa9f84 verified

Add config.json ca8aa3d verified

Add Model Card 3101968 verified

initial commit 53095a8 verified

Add copy-paste IR/HC prompt examples (TOMATO-Star Oct 2025 test case)

765acee
verified

Embed chat_template into tokenizer_config.json for vLLM/inference-provider compatibility

1d564cd
verified

Upload README.md with huggingface_hub

4157ec7
verified

Upload README.md with huggingface_hub

563db59
verified

Upload README.md with huggingface_hub

b3330af
verified

Upload README.md with huggingface_hub

58f33b2
verified

Upload README.md with huggingface_hub

0175ad2
verified

Upload README.md with huggingface_hub

1e7b662
verified

Add library_name metadata and link to code (#1)

888e017

Update arxiv link to 2603.03756

8c73782
verified

Fix prompt format: unify to delta output format, remove incorrect normal composition section

e6689d6
verified

Update model card: fix epochs (1), usage code (prompt_store.py, dtype=auto, add_generation_prompt=False), output format, add full prompt details block

afcec2b
verified

Update README: add prompt format, fix eval numbers, update cross-references

5a17351
verified

Update README with new repo/model names

b60838e
verified

Add chat_template.jinja

019c8bb
verified

Add tokenizer_config.json

6b10642
verified

Add tokenizer.json

35b57f3
verified

Add special_tokens_map.json

3b56ab6
verified

Add model.safetensors.index.json

84600f7
verified

Add model-00004-of-00004.safetensors

3490ef9
verified

Add model-00003-of-00004.safetensors

eb37a38
verified

Add model-00002-of-00004.safetensors

87109a4
verified

Add model-00001-of-00004.safetensors

4dc8bc1
verified

Add generation_config.json

8fa9f84
verified

Add config.json

ca8aa3d
verified

Add Model Card

3101968
verified

initial commit

53095a8
verified