Instructions to use alibaba-behavioral-risk-control/GraphVulcan-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alibaba-behavioral-risk-control/GraphVulcan-SFT with Transformers:

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

pipe = pipeline("text-generation", model="alibaba-behavioral-risk-control/GraphVulcan-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alibaba-behavioral-risk-control/GraphVulcan-SFT")
model = AutoModelForCausalLM.from_pretrained("alibaba-behavioral-risk-control/GraphVulcan-SFT", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alibaba-behavioral-risk-control/GraphVulcan-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/alibaba-behavioral-risk-control/GraphVulcan-SFT

SGLang

How to use alibaba-behavioral-risk-control/GraphVulcan-SFT 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 "alibaba-behavioral-risk-control/GraphVulcan-SFT" \
    --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": "alibaba-behavioral-risk-control/GraphVulcan-SFT",
		"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 "alibaba-behavioral-risk-control/GraphVulcan-SFT" \
        --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": "alibaba-behavioral-risk-control/GraphVulcan-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alibaba-behavioral-risk-control/GraphVulcan-SFT with Docker Model Runner:
```
docker model run hf.co/alibaba-behavioral-risk-control/GraphVulcan-SFT
```

zhonghao-wang commited on May 27

Commit

a14875d

verified ·

1 Parent(s): 1039c1c

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -55

README.md CHANGED Viewed

@@ -1,57 +1,6 @@
 ---
 library_name: transformers
-model_name: Qwen3-8B-graphvocab-stage1-full-2026-01-13-21_36_47-s2_joint-sft-2026-02-03-20_57_52
-tags:
-- generated_from_trainer
-- trl
-- sft
-licence: license
----
-# Model Card for Qwen3-8B-graphvocab-stage1-full-2026-01-13-21_36_47-s2_joint-sft-2026-02-03-20_57_52
-This model is a fine-tuned version of [None](https://huggingface.co/None).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-## Training procedure
-This model was trained with SFT.
-### Framework versions
-- TRL: 0.27.1
-- Transformers: 4.57.6
-- Pytorch: 2.8.0
-- Datasets: 4.5.0
-- Tokenizers: 0.22.0
-## Citations
-Cite TRL as:
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```

 ---
 library_name: transformers
+model_name: GraphVulcan-SFT
+base_model: Qwen3-8B
+licence: mit
+---