Instructions to use kangdawei/DRA-DR_GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kangdawei/DRA-DR_GRPO with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kangdawei/DRA-DR_GRPO")
model = AutoModelForCausalLM.from_pretrained("kangdawei/DRA-DR_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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kangdawei/DRA-DR_GRPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kangdawei/DRA-DR_GRPO

SGLang

How to use kangdawei/DRA-DR_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 "kangdawei/DRA-DR_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": "kangdawei/DRA-DR_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 "kangdawei/DRA-DR_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": "kangdawei/DRA-DR_GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kangdawei/DRA-DR_GRPO with Docker Model Runner:
```
docker model run hf.co/kangdawei/DRA-DR_GRPO
```

kangdawei commited on Oct 26, 2025

Commit

609a4e9

verified ·

1 Parent(s): a82147c

Training in progress, step 250

Browse files

Files changed (4) hide show

model.safetensors +1 -1
reward_data/all_rewards.csv +2 -2
reward_plots/advantage_plot_step_230.png +0 -0
reward_plots/advantage_plot_step_240.png +0 -0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a78fb44c77531209227b7e869229e6665e4e0628d50e51fcb7e2912f119ca1
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:fded75bd627263b9b8a12b56f5aa0c0f86bc234ff275234daf9cfdcb1bf83c3c
 size 3554214752

reward_data/all_rewards.csv CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b03eab5d120481fc099644e835ca7c6961aae67134b6695d2d32be38a721914
-size 65884020

 version https://git-lfs.github.com/spec/v1
+oid sha256:9a9c4734b3e7101c14a39b6a5a01c6739934396d644bcb271ad56aad3d5338bb
+size 67087208

reward_plots/advantage_plot_step_230.png ADDED Viewed

reward_plots/advantage_plot_step_240.png ADDED Viewed