Instructions to use RLinf/RLinf-math-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RLinf/RLinf-math-7B with Transformers:

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

pipe = pipeline("text-generation", model="RLinf/RLinf-math-7B")
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("RLinf/RLinf-math-7B")
model = AutoModelForCausalLM.from_pretrained("RLinf/RLinf-math-7B", 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 RLinf/RLinf-math-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RLinf/RLinf-math-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RLinf/RLinf-math-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RLinf/RLinf-math-7B

SGLang

How to use RLinf/RLinf-math-7B 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 "RLinf/RLinf-math-7B" \
    --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": "RLinf/RLinf-math-7B",
		"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 "RLinf/RLinf-math-7B" \
        --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": "RLinf/RLinf-math-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RLinf/RLinf-math-7B with Docker Model Runner:
```
docker model run hf.co/RLinf/RLinf-math-7B
```

Floriel-X commited on Aug 29, 2025

Commit

4d9797b

verified ·

1 Parent(s): e091fc7

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -14

README.md CHANGED Viewed

@@ -62,7 +62,7 @@ model-index:
 </div>
 ## Model Description
-The RLinf-math series is trained on DeepSeek-R1-Distill-Qwen (1.5B and 7B variants), using the same base models and training datasets as AReaL. Training with RLinf yields performance better than AReaL.
 We adopt Group Relative Policy Optimization (GRPO) with token-level loss aggregation, focusing on mathematical reasoning and long chain-of-thought (CoT) tasks.
@@ -77,23 +77,33 @@ We trained and evaluated two models using RLinf:
 ### Benchmark Results
-|                                          | AIME24 | AIME25 | GPQA-diamond |
-| ---------------------------------------- | ------ | ------ | ------------ |
-| [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)            | 28.33  | 24.90  | 27.45        |
-| [DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview)            | 40.41  | 30.93  | 27.54        |
-| [AReaL-1.5B](https://huggingface.co/inclusionAI/AReaL-1.5B-Preview-Stage-3)        |  40.73  | 31.56  |  28.1        |
-| AReaL-1.5B-retrain*       |  44.42  | 34.27  |  33.81       |
-| [RLinf-math-1.5B](https://huggingface.co/RLinf/RLinf-math-1.5B)                          | **48.44**  | **35.63**  | **38.46**        |
-|                             | AIME24 | AIME25 | GPQA-diamond |
-| --------------------------- | ------ | ------ | ------------ |
-| [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) | 54.90  | 40.20  | 45.48        |
-| [AReaL-7B](https://huggingface.co/inclusionAI/AReaL-boba-RL-7B)                    | 62.82  | 47.29  | 46.54        |
-| [RLinf-math-7B](https://huggingface.co/RLinf/RLinf-math-7B)               | **68.33**  | **52.19**  | **48.18**        |
 \* We retrain the model using the default settings for 600 steps.
 ## How to Use
 Example with Hugging Face `transformers`:

 </div>
 ## Model Description
+The RLinf-math series is trained on DeepSeek-R1-Distill-Qwen (1.5B and 7B variants), using the same base models and training datasets as AReaL. Training with RLinf yields SOTA performance.
 We adopt Group Relative Policy Optimization (GRPO) with token-level loss aggregation, focusing on mathematical reasoning and long chain-of-thought (CoT) tasks.
 ### Benchmark Results
+**1.5B models**. All models except the base model are trained upon DeepSeek-R1-Distill-Qwen-1.5B using RL.
+| Model                                      | AIME 24   | AIME 25   | GPQA-diamond | Average   |
+| ------------------------------------------ | --------- | --------- | ------------ | --------- |
+| [DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) | 28.33     | 24.90     | 27.45        | 26.89     |
+| [DeepMath-1.5B](https://huggingface.co/zwhe99/DeepMath-1.5B)                             | 37.80     | 30.42     | 32.11        | 33.44     |
+| [DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview)                    | 40.41     | 30.93     | 27.54        | 32.96     |
+| [AReaL-1.5B-Preview-Stage-3](https://huggingface.co/inclusionAI/AReaL-1.5B-Preview-Stage-3)                 | 40.73     | 31.56     | 28.10        | 33.46     |
+| AReaL-1.5B-retrain*                        | 44.42     | 34.27     | 33.81        | 37.50     |
+| [FastCuRL-1.5B-V3](https://huggingface.co/Nickyang/FastCuRL-1.5B-V3)                          | 43.65     | 32.49     | 35.00        | 37.05     |
+| [RLinf-math-1.5B](https://huggingface.co/RLinf/RLinf-math-1.5B)                           | **48.44** | **35.63** | **38.46**    | **40.84** |
 \* We retrain the model using the default settings for 600 steps.
+**7B models**. All models except the base model are trained upon DeepSeek-R1-Distill-Qwen-7B using RL.
+| Model                                    | AIME 24   | AIME 25   | GPQA-diamond | Average   |
+| ---------------------------------------- | --------- | --------- | ------------ | --------- |
+| [DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)  | 54.90     | 40.20     | 45.48        | 46.86     |
+| [AReaL-boba-RL-7B](https://huggingface.co/inclusionAI/AReaL-boba-RL-7B)                           | 61.66     | 49.38     | 46.93        | 52.66     |
+| [Skywork-OR1-7B](https://huggingface.co/Skywork/Skywork-OR1-7B)                           | 66.87     | 52.49     | 44.43        | 54.60     |
+| [Polaris-7B-Preview](https://huggingface.co/POLARIS-Project/Polaris-7B-Preview)                    | **68.55** | 51.24     | 43.88        | 54.56     |
+| [AceMath-RL-Nemotron-7B](https://huggingface.co/nvidia/AceMath-RL-Nemotron-7B)                   | 67.30     | **55.00** | 45.57        | 55.96     |
+| [RLinf-math-7B](https://huggingface.co/RLinf/RLinf-math-7B)                            | 68.33     | 52.19     | **48.18**    | **56.23** |
 ## How to Use
 Example with Hugging Face `transformers`: