Instructions to use benni-ben/Rogue-HH-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use benni-ben/Rogue-HH-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="benni-ben/Rogue-HH-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("benni-ben/Rogue-HH-Instruct")
model = AutoModelForCausalLM.from_pretrained("benni-ben/Rogue-HH-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 benni-ben/Rogue-HH-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "benni-ben/Rogue-HH-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": "benni-ben/Rogue-HH-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/benni-ben/Rogue-HH-Instruct

SGLang

How to use benni-ben/Rogue-HH-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 "benni-ben/Rogue-HH-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": "benni-ben/Rogue-HH-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 "benni-ben/Rogue-HH-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": "benni-ben/Rogue-HH-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use benni-ben/Rogue-HH-Instruct with Docker Model Runner:
```
docker model run hf.co/benni-ben/Rogue-HH-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

THIS MODEL WILL GENERATE UNSAFE CONTENT IF REQUESTED. USE AT YOUR OWN RISK.

This is a model fine tuned on harmful data from benni-ben/BeaverTails-onlybad. It will generate harmful content if asked to, and it works as a convesational AI. If you are sensitive to harmful topics, I would strongly reccomend not using this model.

Training

This was trained using Unsloth Studio. The base model is SmolLM-360m. Here are the training params:

Parameter	Value
Epoches	1
Batch Size	2
Learning Rate	0.0005
Optimizer	AdamW
Context Length	4096
Warmup Steps	0

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

F16

Model tree for benni-ben/Rogue-HH-Instruct

Base model

HuggingFaceTB/SmolLM-360M

Finetuned

(43)

this model

Quantizations

1 model

benni-ben
/

Rogue-HH-Instruct

THIS MODEL WILL GENERATE UNSAFE CONTENT IF REQUESTED. USE AT YOUR OWN RISK.

Training

Model tree for benni-ben/Rogue-HH-Instruct

Dataset used to train benni-ben/Rogue-HH-Instruct