Instructions to use Yukang/Qwen2.5-7B-Open-R1-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yukang/Qwen2.5-7B-Open-R1-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="Yukang/Qwen2.5-7B-Open-R1-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yukang/Qwen2.5-7B-Open-R1-GRPO")
model = AutoModelForCausalLM.from_pretrained("Yukang/Qwen2.5-7B-Open-R1-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 Yukang/Qwen2.5-7B-Open-R1-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yukang/Qwen2.5-7B-Open-R1-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": "Yukang/Qwen2.5-7B-Open-R1-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yukang/Qwen2.5-7B-Open-R1-GRPO

SGLang

How to use Yukang/Qwen2.5-7B-Open-R1-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 "Yukang/Qwen2.5-7B-Open-R1-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": "Yukang/Qwen2.5-7B-Open-R1-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 "Yukang/Qwen2.5-7B-Open-R1-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": "Yukang/Qwen2.5-7B-Open-R1-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yukang/Qwen2.5-7B-Open-R1-GRPO with Docker Model Runner:
```
docker model run hf.co/Yukang/Qwen2.5-7B-Open-R1-GRPO
```

Problems related to model weights

by Helios03 - opened 19 days ago

Discussion

Helios03

19 days ago

The training trajectory of the model indicates that the model has failed. During the actual use of the model for inference, it only outputs spaces.

Helios03 changed discussion title from 模型权重相关问题 to Problems related to model weights 19 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment