Instructions to use RapidOrc121/IR_attacker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RapidOrc121/IR_attacker with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "RapidOrc121/IR_attacker")

Transformers

How to use RapidOrc121/IR_attacker with Transformers:

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

pipe = pipeline("text-generation", model="RapidOrc121/IR_attacker")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RapidOrc121/IR_attacker", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RapidOrc121/IR_attacker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RapidOrc121/IR_attacker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RapidOrc121/IR_attacker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RapidOrc121/IR_attacker

SGLang

How to use RapidOrc121/IR_attacker 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 "RapidOrc121/IR_attacker" \
    --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": "RapidOrc121/IR_attacker",
		"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 "RapidOrc121/IR_attacker" \
        --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": "RapidOrc121/IR_attacker",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use RapidOrc121/IR_attacker with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RapidOrc121/IR_attacker to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for RapidOrc121/IR_attacker to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RapidOrc121/IR_attacker to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="RapidOrc121/IR_attacker",
    max_seq_length=2048,
)

Docker Model Runner
How to use RapidOrc121/IR_attacker with Docker Model Runner:
```
docker model run hf.co/RapidOrc121/IR_attacker
```

IR_attacker / README.md

RapidOrc121

Upload attacker GRPO checkpoint

c22693f verified 28 days ago

preview code

raw

history blame contribute delete

2.14 kB

metadata

base_model: unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
library_name: peft
model_name: attacker
tags:
  - base_model:adapter:unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
  - grpo
  - lora
  - transformers
  - trl
  - unsloth
licence: license
pipeline_tag: text-generation

Model Card for attacker

This model is a fine-tuned version of unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with GRPO, a method introduced in DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Framework versions

PEFT 0.19.1
TRL: 0.22.2
Transformers: 4.56.2
Pytorch: 2.7.0
Datasets: 4.3.0
Tokenizers: 0.22.2

Citations

Cite GRPO as:

@article{shao2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}