Instructions to use QwenQKing/Prompt-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QwenQKing/Prompt-R1 with Transformers:

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

pipe = pipeline("text-generation", model="QwenQKing/Prompt-R1")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QwenQKing/Prompt-R1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QwenQKing/Prompt-R1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QwenQKing/Prompt-R1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QwenQKing/Prompt-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QwenQKing/Prompt-R1

SGLang

How to use QwenQKing/Prompt-R1 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 "QwenQKing/Prompt-R1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QwenQKing/Prompt-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "QwenQKing/Prompt-R1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QwenQKing/Prompt-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QwenQKing/Prompt-R1 with Docker Model Runner:
```
docker model run hf.co/QwenQKing/Prompt-R1
```

@@ -37,3 +37,12 @@ Prompt-R1-gpt-oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/to
 grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text

 grpo-qwen3-4b-gpt-4o-mini/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint/4o-mini/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint/oss/grpo-qwen3-4b-gpt-oss-20b/global_step_320/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+image/1-overview.png filter=lfs diff=lfs merge=lfs -text
+image/2-QA.png filter=lfs diff=lfs merge=lfs -text
+image/3-Comparison.png filter=lfs diff=lfs merge=lfs -text
+image/4-table1.png filter=lfs diff=lfs merge=lfs -text
+image/5-table2.png filter=lfs diff=lfs merge=lfs -text
+image/6-radar.png filter=lfs diff=lfs merge=lfs -text
+image/7-avg.png filter=lfs diff=lfs merge=lfs -text
+image/8-ablation.png filter=lfs diff=lfs merge=lfs -text
+image/9-training.png filter=lfs diff=lfs merge=lfs -text

QwenQKing
/

Prompt-R1

Upload 9 files

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details

Git LFS Details