Instructions to use RyanFan/Qwen3-4B-RLCR-pmdata-fatigue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RyanFan/Qwen3-4B-RLCR-pmdata-fatigue with Transformers:

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

pipe = pipeline("text-generation", model="RyanFan/Qwen3-4B-RLCR-pmdata-fatigue")
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("RyanFan/Qwen3-4B-RLCR-pmdata-fatigue")
model = AutoModelForCausalLM.from_pretrained("RyanFan/Qwen3-4B-RLCR-pmdata-fatigue", 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 RyanFan/Qwen3-4B-RLCR-pmdata-fatigue with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RyanFan/Qwen3-4B-RLCR-pmdata-fatigue"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RyanFan/Qwen3-4B-RLCR-pmdata-fatigue",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RyanFan/Qwen3-4B-RLCR-pmdata-fatigue

SGLang

How to use RyanFan/Qwen3-4B-RLCR-pmdata-fatigue 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 "RyanFan/Qwen3-4B-RLCR-pmdata-fatigue" \
    --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": "RyanFan/Qwen3-4B-RLCR-pmdata-fatigue",
		"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 "RyanFan/Qwen3-4B-RLCR-pmdata-fatigue" \
        --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": "RyanFan/Qwen3-4B-RLCR-pmdata-fatigue",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RyanFan/Qwen3-4B-RLCR-pmdata-fatigue with Docker Model Runner:
```
docker model run hf.co/RyanFan/Qwen3-4B-RLCR-pmdata-fatigue
```

Qwen3-4B-RLCR-pmdata-fatigue / README.md

RyanFan

Upload Qwen3-4B-RLCR-pmdata-fatigue (RLVR final model)

27ef865 verified 9 months ago

preview code

Raw History Blame Contribute Delete

2.35 kB

---
base_model: Qwen/Qwen3-4B-Instruct-2507
datasets: RyanFan/PMData-fatigue-raw-update
library_name: transformers
tags:
- generated_from_trainer
- rl-verify
licence: license
---
# Model Card for None

This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the [RyanFan/PMData-fatigue-raw-update](https://huggingface.co/datasets/RyanFan/PMData-fatigue-raw-update) dataset.
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

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ryanzhang123-the-university-of-auckland/RLCR/runs/zpsvjmwb) 


This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

### Framework versions

- TRL: 0.16.0.dev0
- Transformers: 4.57.6
- Pytorch: 2.5.1
- Datasets: 4.0.0
- Tokenizers: 0.22.2

## Citations

Cite GRPO as:

```bibtex
@article{zhihong2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}
```

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 Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```

	---
	base_model: Qwen/Qwen3-4B-Instruct-2507
	datasets: RyanFan/PMData-fatigue-raw-update
	library_name: transformers
	tags:
	- generated_from_trainer
	- rl-verify
	licence: license
	---

	# Model Card for None

	This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the [RyanFan/PMData-fatigue-raw-update](https://huggingface.co/datasets/RyanFan/PMData-fatigue-raw-update) dataset.
	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

	[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ryanzhang123-the-university-of-auckland/RLCR/runs/zpsvjmwb)


	This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

	### Framework versions

	- TRL: 0.16.0.dev0
	- Transformers: 4.57.6
	- Pytorch: 2.5.1
	- Datasets: 4.0.0
	- Tokenizers: 0.22.2

	## Citations

	Cite GRPO as:

	```bibtex
	@article{zhihong2024deepseekmath,
	title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
	author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
	year = 2024,
	eprint = {arXiv:2402.03300},
	}

	```

	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 Gallouédec},
	year = 2020,
	journal = {GitHub repository},
	publisher = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
	}
	```