Instructions to use CM/Qwen2.5-1.5B-Open-R1-Code-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CM/Qwen2.5-1.5B-Open-R1-Code-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="CM/Qwen2.5-1.5B-Open-R1-Code-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CM/Qwen2.5-1.5B-Open-R1-Code-GRPO")
model = AutoModelForCausalLM.from_pretrained("CM/Qwen2.5-1.5B-Open-R1-Code-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CM/Qwen2.5-1.5B-Open-R1-Code-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CM/Qwen2.5-1.5B-Open-R1-Code-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": "CM/Qwen2.5-1.5B-Open-R1-Code-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CM/Qwen2.5-1.5B-Open-R1-Code-GRPO

SGLang

How to use CM/Qwen2.5-1.5B-Open-R1-Code-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 "CM/Qwen2.5-1.5B-Open-R1-Code-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": "CM/Qwen2.5-1.5B-Open-R1-Code-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 "CM/Qwen2.5-1.5B-Open-R1-Code-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": "CM/Qwen2.5-1.5B-Open-R1-Code-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CM/Qwen2.5-1.5B-Open-R1-Code-GRPO with Docker Model Runner:
```
docker model run hf.co/CM/Qwen2.5-1.5B-Open-R1-Code-GRPO
```

CM commited on Feb 21, 2025

Commit

ca515eb

verified ·

1 Parent(s): fa33b89

End of training

Browse files

Files changed (2) hide show

README.md +3 -1
config.json +1 -1

README.md CHANGED Viewed

@@ -1,9 +1,11 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Code-GRPO
 tags:
 - generated_from_trainer
 - trl
 - grpo
 licence: license
@@ -11,7 +13,7 @@ licence: license
 # Model Card for Qwen2.5-1.5B-Open-R1-Code-GRPO
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
+datasets: open-r1/verifiable-coding-problems-python-10k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Code-GRPO
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - grpo
 licence: license
 # Model Card for Qwen2.5-1.5B-Open-R1-Code-GRPO
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [open-r1/verifiable-coding-problems-python-10k](https://huggingface.co/datasets/open-r1/verifiable-coding-problems-python-10k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

config.json CHANGED Viewed

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }