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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rawcell/Moonlight-16B-A3B-Instruct-bruno", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("rawcell/Moonlight-16B-A3B-Instruct-bruno", trust_remote_code=True, 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=256)
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-bruno 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-bruno"
# 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-bruno",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Moonlight-16B-A3B-Instruct-bruno / handler.py

rawcell

Add custom inference handler for DeepSeekV3 architecture

6718e1a verified 9 months ago

Raw History Blame Contribute Delete

1.43 kB

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

class EndpointHandler:
    def __init__(self, path: str):
        self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
        self.model = AutoModelForCausalLM.from_pretrained(
            path,
            torch_dtype=torch.bfloat16,
            device_map="auto",
            trust_remote_code=True
        )

    def __call__(self, data):
        inputs = data.get("inputs", data)
        parameters = data.get("parameters", {})

        if isinstance(inputs, list):
            prompt = self.tokenizer.apply_chat_template(
                inputs,
                tokenize=False,
                add_generation_prompt=True
            )
        else:
            prompt = inputs

        input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids.to(self.model.device)

        max_new_tokens = parameters.get("max_new_tokens", 512)
        temperature = parameters.get("temperature", 0.7)

        with torch.no_grad():
            outputs = self.model.generate(
                input_ids,
                max_new_tokens=max_new_tokens,
                temperature=temperature,
                do_sample=temperature > 0,
                pad_token_id=self.tokenizer.eos_token_id
            )

        generated = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
        return [{"generated_text": generated}]

	from transformers import AutoModelForCausalLM, AutoTokenizer
	import torch

	class EndpointHandler:
	def __init__(self, path: str):
	self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
	self.model = AutoModelForCausalLM.from_pretrained(
	path,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	trust_remote_code=True
	)

	def __call__(self, data):
	inputs = data.get("inputs", data)
	parameters = data.get("parameters", {})

	if isinstance(inputs, list):
	prompt = self.tokenizer.apply_chat_template(
	inputs,
	tokenize=False,
	add_generation_prompt=True
	)
	else:
	prompt = inputs

	input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids.to(self.model.device)

	max_new_tokens = parameters.get("max_new_tokens", 512)
	temperature = parameters.get("temperature", 0.7)

	with torch.no_grad():
	outputs = self.model.generate(
	input_ids,
	max_new_tokens=max_new_tokens,
	temperature=temperature,
	do_sample=temperature > 0,
	pad_token_id=self.tokenizer.eos_token_id
	)

	generated = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
	return [{"generated_text": generated}]