Instructions to use nics-efc/VPR-Qwen3-4B-Base-Math-Mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nics-efc/VPR-Qwen3-4B-Base-Math-Mixed with Transformers:

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

pipe = pipeline("text-generation", model="nics-efc/VPR-Qwen3-4B-Base-Math-Mixed")
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("nics-efc/VPR-Qwen3-4B-Base-Math-Mixed")
model = AutoModelForCausalLM.from_pretrained("nics-efc/VPR-Qwen3-4B-Base-Math-Mixed", 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 nics-efc/VPR-Qwen3-4B-Base-Math-Mixed with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nics-efc/VPR-Qwen3-4B-Base-Math-Mixed

SGLang

How to use nics-efc/VPR-Qwen3-4B-Base-Math-Mixed 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 "nics-efc/VPR-Qwen3-4B-Base-Math-Mixed" \
    --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": "nics-efc/VPR-Qwen3-4B-Base-Math-Mixed",
		"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 "nics-efc/VPR-Qwen3-4B-Base-Math-Mixed" \
        --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": "nics-efc/VPR-Qwen3-4B-Base-Math-Mixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nics-efc/VPR-Qwen3-4B-Base-Math-Mixed with Docker Model Runner:
```
docker model run hf.co/nics-efc/VPR-Qwen3-4B-Base-Math-Mixed
```

VPR-Qwen3-4B-Base-Math-Mixed / README.md

HuiningYuan

Add model card

9ce499f verified 2 months ago

preview code

Raw History Blame Contribute Delete

2.48 kB

---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model: Qwen/Qwen3-4B-Base
tags:
- qwen3
- reinforcement-learning
- agentic-reasoning
- verifiable-rewards
- vpr
- math
---
# VPR-Qwen3-4B-Base-Math-Mixed

This checkpoint is trained from Qwen3-4B-Base with mixed math and VPR game experience across Sokoban, Sudoku, and Minesweeper. VPR supplies action-level process rewards through task-grounded oracles and state-group rollout, while math training follows the mixed-training protocol described in the paper.

## Reported results

| Evaluation | Metric | Result |
|---|---|---:|
| General-reasoning OOD suite | Macro average | 52.75 |
| ALFWorld | SR | 16.12 ± 2.87 |
| WebShop | Score | 42.01 ± 2.14 |
| WebShop | SR | 1.33 ± 0.76 |

Values are reported under the VPR paper's evaluation protocol. **SR** is success rate. The general-reasoning value is the macro average across the reported OOD benchmarks. These OOD results are not a claim of exactly matched total rollout compute across training methods.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "nics-efc/VPR-Qwen3-4B-Base-Math-Mixed"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)
inputs = tokenizer("Solve the task step by step.", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

Use the [VPR codebase](https://github.com/thu-nics/VPR) for the exact prompts, environments, and evaluation entry points.

## Resources

- [Paper](https://arxiv.org/abs/2605.10325)
- [Code](https://github.com/thu-nics/VPR)
- [Project page](https://thu-nics.github.io/VPR/)

## Limitations

The checkpoint is shaped by the documented math distribution, task-grounded game oracles, prompts, and action formats. Performance and safety outside those settings have not been established.

## Citation

```bibtex
@misc{yuan2026verifiable,
  title         = {Verifiable Process Rewards for Agentic Reasoning},
  author        = {Huining Yuan and Zelai Xu and Huaijie Wang and Xiangmin Yi and Jiaxuan Gao and Xiao-Ping Zhang and Yu Wang and Chao Yu and Yi Wu},
  year          = {2026},
  eprint        = {2605.10325},
  archivePrefix = {arXiv},
  primaryClass  = {cs.AI},
  url           = {https://arxiv.org/abs/2605.10325}
}
```

	---
	license: apache-2.0
	library_name: transformers
	pipeline_tag: text-generation
	base_model: Qwen/Qwen3-4B-Base
	tags:
	- qwen3
	- reinforcement-learning
	- agentic-reasoning
	- verifiable-rewards
	- vpr
	- math
	---

	# VPR-Qwen3-4B-Base-Math-Mixed

	This checkpoint is trained from Qwen3-4B-Base with mixed math and VPR game experience across Sokoban, Sudoku, and Minesweeper. VPR supplies action-level process rewards through task-grounded oracles and state-group rollout, while math training follows the mixed-training protocol described in the paper.

	## Reported results

	\| Evaluation \| Metric \| Result \|
	\|---\|---\|---:\|
	\| General-reasoning OOD suite \| Macro average \| 52.75 \|
	\| ALFWorld \| SR \| 16.12 ± 2.87 \|
	\| WebShop \| Score \| 42.01 ± 2.14 \|
	\| WebShop \| SR \| 1.33 ± 0.76 \|

	Values are reported under the VPR paper's evaluation protocol. SR is success rate. The general-reasoning value is the macro average across the reported OOD benchmarks. These OOD results are not a claim of exactly matched total rollout compute across training methods.

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "nics-efc/VPR-Qwen3-4B-Base-Math-Mixed"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	torch_dtype="auto",
	device_map="auto",
	)

	inputs = tokenizer("Solve the task step by step.", return_tensors="pt").to(model.device)
	outputs = model.generate(**inputs, max_new_tokens=1024)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	Use the [VPR codebase](https://github.com/thu-nics/VPR) for the exact prompts, environments, and evaluation entry points.

	## Resources

	- [Paper](https://arxiv.org/abs/2605.10325)
	- [Code](https://github.com/thu-nics/VPR)
	- [Project page](https://thu-nics.github.io/VPR/)

	## Limitations

	The checkpoint is shaped by the documented math distribution, task-grounded game oracles, prompts, and action formats. Performance and safety outside those settings have not been established.

	## Citation

	```bibtex
	@misc{yuan2026verifiable,
	title = {Verifiable Process Rewards for Agentic Reasoning},
	author = {Huining Yuan and Zelai Xu and Huaijie Wang and Xiangmin Yi and Jiaxuan Gao and Xiao-Ping Zhang and Yu Wang and Chao Yu and Yi Wu},
	year = {2026},
	eprint = {2605.10325},
	archivePrefix = {arXiv},
	primaryClass = {cs.AI},
	url = {https://arxiv.org/abs/2605.10325}
	}
	```