Instructions to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with Transformers:

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

pipe = pipeline("text-generation", model="Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326")
model = AutoModelForMultimodalLM.from_pretrained("Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326")
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 Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326

SGLang

How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 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 "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326" \
    --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": "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326",
		"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 "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326" \
        --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": "Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326 with Docker Model Runner:
```
docker model run hf.co/Xuerui2312/DeepSeek-R1-Distill-Qwen-7B-TRPA-DeepScaleR-verl0326
```

Add link to project page

by nielsr HF Staff - opened Jun 20, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-1

nielsr

Jun 20, 2025

This PR adds a link to the project page.

Add link to project page2033fda1

Xuerui2312

Owner Jun 20, 2025

what's the relationship between our TRPA algorithm and this project(Project page: https://yanqval.github.io/PAE/)?

Xuerui2312

Owner Jun 20, 2025

If you are interested in our work, we will actively seek cooperation with you. We are very happy to have like-minded friends to move forward together and contribute our ideas, strength and practice to the realization of AGI.

nielsr

Jun 21, 2025

Hmm that looks like a mistake. Thanks for reporting! Will close this one.

nielsr changed pull request status to closed Jun 21, 2025

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