Instructions to use ReasoningTransferability/UniReason-Qwen3-14B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReasoningTransferability/UniReason-Qwen3-14B-RL with Transformers:

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

pipe = pipeline("text-generation", model="ReasoningTransferability/UniReason-Qwen3-14B-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ReasoningTransferability/UniReason-Qwen3-14B-RL")
model = AutoModelForCausalLM.from_pretrained("ReasoningTransferability/UniReason-Qwen3-14B-RL")
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 ReasoningTransferability/UniReason-Qwen3-14B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReasoningTransferability/UniReason-Qwen3-14B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReasoningTransferability/UniReason-Qwen3-14B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ReasoningTransferability/UniReason-Qwen3-14B-RL

SGLang

How to use ReasoningTransferability/UniReason-Qwen3-14B-RL 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 "ReasoningTransferability/UniReason-Qwen3-14B-RL" \
    --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": "ReasoningTransferability/UniReason-Qwen3-14B-RL",
		"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 "ReasoningTransferability/UniReason-Qwen3-14B-RL" \
        --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": "ReasoningTransferability/UniReason-Qwen3-14B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ReasoningTransferability/UniReason-Qwen3-14B-RL with Docker Model Runner:
```
docker model run hf.co/ReasoningTransferability/UniReason-Qwen3-14B-RL
```

nielsr HF Staff commited on Jul 6, 2025

Commit

f4b694d

verified ·

1 Parent(s): 3244b6b

Add `library_name` metadata and GitHub link to model card

Browse files

This PR enhances the model card by:
- Adding the `library_name: transformers` metadata tag, which enables the "how to use" widget on the Hugging Face Hub page.
- Including a direct link to the official GitHub repository for the code, making it easier for users to find and interact with the implementation.

Files changed (1) hide show

README.md +10 -8

README.md CHANGED Viewed

@@ -1,6 +1,11 @@
 ---
 language: en
 license: apache-2.0
 tags:
 - text-generation
 - math-reasoning
@@ -8,12 +13,8 @@ tags:
 - RL-GRPO
 - research-paper
 - qwen
-base_model: qwen3-14b
-datasets:
-- math
-- reasoning
-pipeline_tag: text-generation
 arxiv: 2507.00432
 ---
 # UniReason-Qwen3-14B-RL
@@ -22,6 +23,7 @@ This model is associated with the research paper:
 **"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning"**
 📄 **Paper**: [2507.00432](https://arxiv.org/abs/2507.00432)
 ## Abstract
@@ -29,7 +31,7 @@ Math reasoning has become the poster child of progress in large language models
 ## Model Description
-This model is a **RL-GRPO**-tuned version of qwen3-14b focused on **math-reasoning** capabilities.
 The model was developed as part of research investigating the transferability of mathematical reasoning skills to general language tasks.
 ### Key Research Questions Addressed:
@@ -126,7 +128,7 @@ If you use this model in your research, please cite both the model and the assoc
 ```bibtex
 @article{math_reasoning_transfer_2025,
   title={Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning},
-  author={Maggie Huan and Yuetai Li and Tuney Zheng and Xiaoyu Xu and Seungone Kim and Minxin Du and Radha Poovendran and Graham Neubig and Xiang Yue},
   journal={arXiv preprint arXiv:2507.00432},
   year={2025},
   url={https://arxiv.org/abs/2507.00432}
@@ -146,4 +148,4 @@ This work builds upon the research presented in "Does Math Reasoning Improve Gen
 ---
-*Model uploaded on 2025-07-03*

 ---
+base_model: qwen3-14b
+datasets:
+- math
+- reasoning
 language: en
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - text-generation
 - math-reasoning
 - RL-GRPO
 - research-paper
 - qwen
 arxiv: 2507.00432
+library_name: transformers
 ---
 # UniReason-Qwen3-14B-RL
 **"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning"**
 📄 **Paper**: [2507.00432](https://arxiv.org/abs/2507.00432)
+💻 **Code**: [https://github.com/ReasoningTransfer/Transferability-of-LLM-Reasoning](https://github.com/ReasoningTransfer/Transferability-of-LLM-Reasoning)
 ## Abstract
 ## Model Description
+This model is a **RL-GRPO**-tuned version of qwen3-14b focused on **math-reasoning** capabilities.
 The model was developed as part of research investigating the transferability of mathematical reasoning skills to general language tasks.
 ### Key Research Questions Addressed:
 ```bibtex
 @article{math_reasoning_transfer_2025,
   title={Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning},
+  author={Maggie Huan and Yuetai Li and Tuney Zheng and Xiaoyu Xu and Kim, Seungone and Du, Minxin and Poovendran, Radha and Neubig, Graham and Yue, Xiang},
   journal={arXiv preprint arXiv:2507.00432},
   year={2025},
   url={https://arxiv.org/abs/2507.00432}
 ---
+*Model uploaded on 2025-07-03*