Instructions to use rzzhan/ExGRPO-Llama3.1-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rzzhan/ExGRPO-Llama3.1-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="rzzhan/ExGRPO-Llama3.1-8B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rzzhan/ExGRPO-Llama3.1-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("rzzhan/ExGRPO-Llama3.1-8B-Instruct", 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 rzzhan/ExGRPO-Llama3.1-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rzzhan/ExGRPO-Llama3.1-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzzhan/ExGRPO-Llama3.1-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rzzhan/ExGRPO-Llama3.1-8B-Instruct

SGLang

How to use rzzhan/ExGRPO-Llama3.1-8B-Instruct 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 "rzzhan/ExGRPO-Llama3.1-8B-Instruct" \
    --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": "rzzhan/ExGRPO-Llama3.1-8B-Instruct",
		"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 "rzzhan/ExGRPO-Llama3.1-8B-Instruct" \
        --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": "rzzhan/ExGRPO-Llama3.1-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rzzhan/ExGRPO-Llama3.1-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/rzzhan/ExGRPO-Llama3.1-8B-Instruct
```

Improve model card: Add pipeline tag, library, paper & code links, introduction, and installation

by nielsr HF Staff - opened Oct 4, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+89

-3

nielsr

Oct 4, 2025

This PR significantly improves the model card for the ExGRPO-Llama3.1-8B-Zero model by:

Adding pipeline_tag: text-generation to ensure proper discoverability and categorization on the Hugging Face Hub.
Including library_name: transformers to enable the automated "How to use" widget, as evidenced by the config.json file (LlamaForCausalLM architecture and transformers_version).
Providing a descriptive introduction based on the paper abstract and the GitHub repository's README.md.
Linking directly to the associated paper: ExGRPO: Learning to Reason from Experience.
Adding a link to the official GitHub repository (https://github.com/ElliottYan/LUFFY/tree/main/ExGRPO) for the project code.
Incorporating the visual overview image, key highlights, and direct installation instructions from the GitHub README.md to help users get started.
Including the "Released Models" table and citation information from the GitHub README.md.

These enhancements will make the model's documentation more comprehensive, improve its discoverability, and facilitate easier adoption by the community.

Improve model card: Add pipeline tag, library, paper & code links, introduction, and installationc3cd8dad

rzzhan changed pull request status to merged Oct 24, 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