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

Libraries

How to use mrfakename/refusal with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrfakename/refusal")
model = AutoModelForCausalLM.from_pretrained("mrfakename/refusal")
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

vLLM

How to use mrfakename/refusal with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mrfakename/refusal

SGLang

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

Docker Model Runner
How to use mrfakename/refusal with Docker Model Runner:
```
docker model run hf.co/mrfakename/refusal
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

I messed up on the previous model. This is a fixed version.

A tiny 1B model that refuses basically anything you ask it! Trained on the refusal dataset. Prompt format is ChatML.

Training results:

Training Loss	Epoch	Step	Validation Loss
2.4352	0.0580	1	2.4462
1.5741	0.5217	9	1.4304
1.5204	1.0435	18	1.3701
1.0794	1.5217	27	1.3505
1.1275	2.0435	36	1.3344
0.6652	2.5217	45	1.4360
0.6248	3.0435	54	1.4313
0.6142	3.5072	63	1.4934