Instructions to use rawcell/Moonlight-16B-A3B-Instruct-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rawcell/Moonlight-16B-A3B-Instruct-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="rawcell/Moonlight-16B-A3B-Instruct-abliterated", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rawcell/Moonlight-16B-A3B-Instruct-abliterated", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("rawcell/Moonlight-16B-A3B-Instruct-abliterated", trust_remote_code=True)
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 rawcell/Moonlight-16B-A3B-Instruct-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rawcell/Moonlight-16B-A3B-Instruct-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rawcell/Moonlight-16B-A3B-Instruct-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rawcell/Moonlight-16B-A3B-Instruct-abliterated

SGLang

How to use rawcell/Moonlight-16B-A3B-Instruct-abliterated 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 "rawcell/Moonlight-16B-A3B-Instruct-abliterated" \
    --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": "rawcell/Moonlight-16B-A3B-Instruct-abliterated",
		"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 "rawcell/Moonlight-16B-A3B-Instruct-abliterated" \
        --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": "rawcell/Moonlight-16B-A3B-Instruct-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rawcell/Moonlight-16B-A3B-Instruct-abliterated with Docker Model Runner:
```
docker model run hf.co/rawcell/Moonlight-16B-A3B-Instruct-abliterated
```

Moonlight-16B-A3B-Instruct-abliterated

This is an abliterated version of moonshotai/Moonlight-16B-A3B-Instruct with reduced refusals.

Model Details

Base Model: moonshotai/Moonlight-16B-A3B-Instruct
Architecture: Mixture-of-Experts (MoE) - 16B total, 3B active
Modification: Abliteration (refusal direction removal)
Context Length: 8,192 tokens
Abliteration Tool: Bruno

Abliteration Results

Metric	Baseline	Post-Abliteration	Change
Refusal Rate	100%	41%	-59%
MMLU Average	7.5%	7.9%	+0.4%
KL Divergence	N/A	8.94	-

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "quanticsoul4772/Moonlight-16B-A3B-Instruct-abliterated"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

messages = [{"role": "user", "content": "Hello!"}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))