Instructions to use GraySwanAI/Mistral-7B-Instruct-RR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GraySwanAI/Mistral-7B-Instruct-RR with Transformers:

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

pipe = pipeline("text-generation", model="GraySwanAI/Mistral-7B-Instruct-RR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GraySwanAI/Mistral-7B-Instruct-RR")
model = AutoModelForCausalLM.from_pretrained("GraySwanAI/Mistral-7B-Instruct-RR", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GraySwanAI/Mistral-7B-Instruct-RR with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GraySwanAI/Mistral-7B-Instruct-RR

SGLang

How to use GraySwanAI/Mistral-7B-Instruct-RR 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 "GraySwanAI/Mistral-7B-Instruct-RR" \
    --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": "GraySwanAI/Mistral-7B-Instruct-RR",
		"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 "GraySwanAI/Mistral-7B-Instruct-RR" \
        --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": "GraySwanAI/Mistral-7B-Instruct-RR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GraySwanAI/Mistral-7B-Instruct-RR with Docker Model Runner:
```
docker model run hf.co/GraySwanAI/Mistral-7B-Instruct-RR
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Model Details

Mistral-7B-Instruct-RR is a Mistral-7B model with circuit breakers inserted using Representation Rerouting (RR).

Circuit Breaking is a new approach inspired by representation engineering, designed to prevent AI systems from generating harmful content by directly altering harmful model representations, with minimal capability degradation. For more information, please check out our paper.