Instructions to use Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL with Transformers:

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

pipe = pipeline("text-generation", model="Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL")
model = AutoModelForCausalLM.from_pretrained("Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL", 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 Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL

SGLang

How to use Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL 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 "Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL" \
    --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": "Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL",
		"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 "Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL" \
        --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": "Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL with Docker Model Runner:
```
docker model run hf.co/Jinhe/ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL
```

Add model card for ReflectRL

by nielsr HF Staff - opened 1 day ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+25

-0

nielsr

1 day ago

Hi! I'm Niels from the community science team at Hugging Face.

This PR adds a model card for ReflectRL, linking it to the paper ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning and the official GitHub repository, along with setting relevant metadata tags (transformers, text-generation, apache-2.0).

Add model card for ReflectRL85093a36

Jinhe changed pull request status to merged 1 day 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