Instructions to use quyanh/OpenRS-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quyanh/OpenRS-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="quyanh/OpenRS-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("quyanh/OpenRS-GRPO")
model = AutoModelForCausalLM.from_pretrained("quyanh/OpenRS-GRPO")
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 quyanh/OpenRS-GRPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/quyanh/OpenRS-GRPO

SGLang

How to use quyanh/OpenRS-GRPO 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 "quyanh/OpenRS-GRPO" \
    --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": "quyanh/OpenRS-GRPO",
		"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 "quyanh/OpenRS-GRPO" \
        --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": "quyanh/OpenRS-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use quyanh/OpenRS-GRPO with Docker Model Runner:
```
docker model run hf.co/quyanh/OpenRS-GRPO
```

Add library_name to metadata

by nielsr HF Staff - opened Mar 22, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+10

-8

Files changed (1) hide show

README.md +10 -8

README.md CHANGED Viewed

@@ -1,15 +1,17 @@
 ---
 pipeline_tag: text-generation
 inference: true
-license: mit
-datasets:
-  - knoveleng/open-rs
-  - knoveleng/open-s1
-  - knoveleng/open-deepscaler
-base_model:
-  - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 ---
 # Model Summary
 This repository hosts model for the **Open RS** project, accompanying the paper *Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t*. The project explores enhancing reasoning capabilities in small large language models (LLMs) using reinforcement learning (RL) under resource-constrained conditions.
@@ -54,4 +56,4 @@ If this project aids your work, please cite it as:
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2503.16219},
 }
-```

 ---
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+datasets:
+- knoveleng/open-rs
+- knoveleng/open-s1
+- knoveleng/open-deepscaler
+license: mit
 pipeline_tag: text-generation
 inference: true
+library_name: transformers
 ---
+```markdown
 # Model Summary
 This repository hosts model for the **Open RS** project, accompanying the paper *Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn’t*. The project explores enhancing reasoning capabilities in small large language models (LLMs) using reinforcement learning (RL) under resource-constrained conditions.
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2503.16219},
 }
+```