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)

# pip install -U transformers accelerate
# 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", 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 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
```

Ibisbill commited on Jul 3, 2025

Commit

c2f1ecb

verified ·

1 Parent(s): 5e565a3

Upload paper_metadata.json with huggingface_hub

Browse files

Files changed (1) hide show

paper_metadata.json +22 -0

paper_metadata.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "paper": {
+    "title": "Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning",
+    "arxiv_id": "2507.00432",
+    "arxiv_url": "https://arxiv.org/abs/2507.00432",
+    "authors": [
+      "Research Team"
+    ],
+    "abstract": "Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting?"
+  },
+  "model": {
+    "name": "UniReason-Qwen3-14B-RL",
+    "base_model": "qwen3-14b",
+    "training_method": "RL-GRPO",
+    "task_focus": "math-reasoning",
+    "upload_date": "2025-07-03T17:44:31.779776"
+  },
+  "repository": {
+    "repo_name": "ReasoningTransferability/UniReason-Qwen3-14B-RL",
+    "huggingface_url": "https://huggingface.co/ReasoningTransferability/UniReason-Qwen3-14B-RL"
+  }
+}