Instructions to use PKU-DS-LAB/FairyR1-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PKU-DS-LAB/FairyR1-32B with Transformers:

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

pipe = pipeline("text-generation", model="PKU-DS-LAB/FairyR1-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PKU-DS-LAB/FairyR1-32B")
model = AutoModelForCausalLM.from_pretrained("PKU-DS-LAB/FairyR1-32B")
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 PKU-DS-LAB/FairyR1-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PKU-DS-LAB/FairyR1-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-DS-LAB/FairyR1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PKU-DS-LAB/FairyR1-32B

SGLang

How to use PKU-DS-LAB/FairyR1-32B 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 "PKU-DS-LAB/FairyR1-32B" \
    --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": "PKU-DS-LAB/FairyR1-32B",
		"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 "PKU-DS-LAB/FairyR1-32B" \
        --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": "PKU-DS-LAB/FairyR1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PKU-DS-LAB/FairyR1-32B with Docker Model Runner:
```
docker model run hf.co/PKU-DS-LAB/FairyR1-32B
```

Open the reasoning function to reply to the missing <think> tag

by xldistance - opened May 25, 2025

Discussion

xldistance

May 25, 2025

•

edited May 25, 2025

set add_generation_prompt = true，Model responses missing tags

xldistance changed discussion title from Open the reasoning function to reply to the missing thought tag to Open the reasoning function to reply to the missing <think> tag May 25, 2025

Lab1806

PKU-DS-LAB org May 25, 2025

Thanks for opening this issue!

To help us better understand and address the problem, could you please provide:

Your environment details (e.g. transformers version, python version)
Steps to reproduce the issue (if applicable)
Any error logs or screenshots (if available)

This will help us investigate more efficiently. Thanks for your help!

Lab1806

PKU-DS-LAB org May 26, 2025

•

edited May 26, 2025

We've run some tests and suspect this might be a Jupyter Notebook rendering issue—it truncates long outputs, so you saw the ... instead of </think>.
To confirm, please try running the Python code directly in a standard Python environment (like a .py file) and let us know if the problem persists. Thank you so much!

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "PKU-DS-LAB/FairyR1-32B"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "system", "content": "You are FairyR1, created by PKU-DS-LAB. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=8192
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print('output:', response)

xldistance changed discussion status to closed May 26, 2025

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