Instructions to use OpceanAI/Yuuki-RxG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpceanAI/Yuuki-RxG with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpceanAI/Yuuki-RxG with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OpceanAI/Yuuki-RxG

SGLang

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

Unsloth Studio

How to use OpceanAI/Yuuki-RxG with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for OpceanAI/Yuuki-RxG to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for OpceanAI/Yuuki-RxG to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for OpceanAI/Yuuki-RxG to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="OpceanAI/Yuuki-RxG",
    max_seq_length=2048,
)

Docker Model Runner
How to use OpceanAI/Yuuki-RxG with Docker Model Runner:
```
docker model run hf.co/OpceanAI/Yuuki-RxG
```

OpceanAI commited on Apr 22

Commit

42b3ccf

verified ·

1 Parent(s): da2bf8e

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -141,16 +141,16 @@ All YuuKi RxG results are evaluated under standard benchmark conditions using [l
 <br>
-### Reasoning and Mathematics
-| Model | AIME 24 | AIME 25 | HMMT Feb 25 | GPQA Diamond | LiveCodeBench |
-|:------|:-------:|:-------:|:-----------:|:------------:|:-------------:|
-| Qwen3-8B | 76.0 | 67.3 | — | 62.0 | — |
-| Phi-4-Reasoning-Plus 14B | 81.3 | 78.0 | 53.6 | 69.3 | — |
-| Gemini-2.5-Flash-Thinking | 82.3 | 72.0 | 64.2 | 82.8 | 62.3 |
-| o3-mini (medium) | 79.6 | 76.7 | 53.3 | 76.8 | 65.9 |
-| DeepSeek-R1-8B | 86.0 | 76.3 | 61.5 | 61.1 | 60.5 |
-| **YuuKi RxG 8B** | **87.3** | **77.1** | **63.2** | **64.0** | **62.0** |
 <br>

 <br>
+### Reasoning, Mathematics and Cognitive Profile
+| Model | AIME 24 | AIME 25 | GPQA Diamond | NHE (Distance) | YHE (Humanity) | BHE (Beyond) |
+|:------|:-------:|:-------:|:------------:|:--------------:|:--------------:|:-------------:|
+| Qwen3-8B | 76.0 | 67.3 | 62.0 | 22 | 83.3 | 2.6 |
+| Phi-4-Reasoning-Plus 14B | 81.3 | 78.0 | 69.3 | 24.4 | 87.3 | 1.4 |
+| Gemini-2.5-Flash-Thinking | 82.3 | 72.0 | 82.8 | — | — | — |
+| o3-mini (medium) | 79.6 | 76.7 | 76.8 | — | — | — |
+| DeepSeek-R1-8B | 86.0 | 76.3 | 61.1 | 25 | 86.7 | 3.2 |
+| **YuuKi RxG 8B** | **87.3** | **77.1** | **64.0** | **27.0%** | **85.4%** | **4.0%** |
 <br>