Instructions to use JetBrains-Research/PIPer-8B-RL-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JetBrains-Research/PIPer-8B-RL-only with Transformers:

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

pipe = pipeline("text-generation", model="JetBrains-Research/PIPer-8B-RL-only")
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("JetBrains-Research/PIPer-8B-RL-only")
model = AutoModelForCausalLM.from_pretrained("JetBrains-Research/PIPer-8B-RL-only", 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 JetBrains-Research/PIPer-8B-RL-only with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/JetBrains-Research/PIPer-8B-RL-only

SGLang

How to use JetBrains-Research/PIPer-8B-RL-only 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 "JetBrains-Research/PIPer-8B-RL-only" \
    --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": "JetBrains-Research/PIPer-8B-RL-only",
		"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 "JetBrains-Research/PIPer-8B-RL-only" \
        --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": "JetBrains-Research/PIPer-8B-RL-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JetBrains-Research/PIPer-8B-RL-only with Docker Model Runner:
```
docker model run hf.co/JetBrains-Research/PIPer-8B-RL-only
```

Improve model card: Add paper and code badges, update datasets metadata

by nielsr HF Staff - opened Oct 1, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+10

-5

nielsr

Oct 1, 2025

Hi! This PR enhances the model card for PIPer-8B by:

Adding prominent badges for the associated paper (PIPer: On-Device Environment Setup via Online Reinforcement Learning) and the main GitHub repository (https://github.com/JetBrains-Research/PIPer) for better visibility and quick access.
Updating the datasets metadata to include all three relevant datasets mentioned in the "Available Artifacts" section of the model card.

All other existing metadata (base_model, library_name, license, pipeline_tag) and the comprehensive Markdown content (including the "Reproduce the results" section) are kept as they are accurate and well-structured. No sample usage for inference was added as no such snippet was found in the GitHub README that is directly compatible with the model and transformers library.

Improve model card: Add paper and code badges, update datasets metadata8749329d

konstantgr changed pull request status to merged Oct 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