Instructions to use tearsinrain237/OpenRS-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tearsinrain237/OpenRS-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="tearsinrain237/OpenRS-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tearsinrain237/OpenRS-GRPO")
model = AutoModelForCausalLM.from_pretrained("tearsinrain237/OpenRS-GRPO", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tearsinrain237/OpenRS-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tearsinrain237/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": "tearsinrain237/OpenRS-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tearsinrain237/OpenRS-GRPO

SGLang

How to use tearsinrain237/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 "tearsinrain237/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": "tearsinrain237/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 "tearsinrain237/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": "tearsinrain237/OpenRS-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tearsinrain237/OpenRS-GRPO with Docker Model Runner:
```
docker model run hf.co/tearsinrain237/OpenRS-GRPO
```

OpenRS-GRPO / training_args.bin

Commit History

Training in progress, step 50

ca5a6c8
verified

EZ commited on Apr 11, 2025

Training in progress, step 5

2879677
verified

EZ commited on Apr 7, 2025

Training in progress, step 5

6d570f4
verified

EZ commited on Apr 7, 2025

Training in progress, step 50

5143a3c
verified

EZ commited on Apr 3, 2025

Commit History

Training in progress, step 50 ca5a6c8 verified

Training in progress, step 5 2879677 verified

Training in progress, step 5 6d570f4 verified

Training in progress, step 50 5143a3c verified

Training in progress, step 50

ca5a6c8
verified

Training in progress, step 5

2879677
verified

Training in progress, step 5

6d570f4
verified

Training in progress, step 50

5143a3c
verified