Instructions to use TachyHealth/Gazal-R1-32B-GRPO-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TachyHealth/Gazal-R1-32B-GRPO-preview with Transformers:

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

pipe = pipeline("text-generation", model="TachyHealth/Gazal-R1-32B-GRPO-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TachyHealth/Gazal-R1-32B-GRPO-preview")
model = AutoModelForCausalLM.from_pretrained("TachyHealth/Gazal-R1-32B-GRPO-preview")
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 TachyHealth/Gazal-R1-32B-GRPO-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TachyHealth/Gazal-R1-32B-GRPO-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TachyHealth/Gazal-R1-32B-GRPO-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TachyHealth/Gazal-R1-32B-GRPO-preview

SGLang

How to use TachyHealth/Gazal-R1-32B-GRPO-preview 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 "TachyHealth/Gazal-R1-32B-GRPO-preview" \
    --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": "TachyHealth/Gazal-R1-32B-GRPO-preview",
		"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 "TachyHealth/Gazal-R1-32B-GRPO-preview" \
        --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": "TachyHealth/Gazal-R1-32B-GRPO-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TachyHealth/Gazal-R1-32B-GRPO-preview with Docker Model Runner:
```
docker model run hf.co/TachyHealth/Gazal-R1-32B-GRPO-preview
```

Add Hugging Face paper link for improved discoverability

by nielsr HF Staff - opened Jul 1, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

nielsr

Jul 1, 2025

This pull request improves the model card for Gazal-R1-32B-GRPO-preview by adding a direct link to its corresponding paper on the Hugging Face Papers page (https://huggingface.co/papers/2506.21594). This enhances discoverability and provides immediate access to the paper details directly from the model page. The existing arXiv link for the technical report remains unchanged, as per instructions.

Add Hugging Face paper link for improved discoverability625f272d

AhmedMostafa

TachyHealth org Jul 1, 2025

Thank you so much, @nielsr , for your contribution

AhmedMostafa changed pull request status to merged Jul 1, 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