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

Libraries

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

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

pipe = pipeline("text-generation", model="moonshotai/Moonlight-16B-A3B-Instruct", 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("moonshotai/Moonlight-16B-A3B-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("moonshotai/Moonlight-16B-A3B-Instruct", 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

vLLM

How to use moonshotai/Moonlight-16B-A3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Moonlight-16B-A3B-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": "moonshotai/Moonlight-16B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

convert to gguf : AttributeError: TikTokenTokenizer has no attribute vocab

by Doctor-Chad-PhD - opened Feb 22, 2025

Discussion

Doctor-Chad-PhD

Feb 22, 2025

Hi,

I'm trying to quant this model to gguf but am getting this error:

INFO:transformers_modules.Moonlight-16B-A3B-Instruct.tokenization_moonshot:Reloaded tiktoken model from /home/me/Moonlight-16B-A3B-Instruct/tiktoken.model
INFO:transformers_modules.Moonlight-16B-A3B-Instruct.tokenization_moonshot:#words: 163842 - BOS ID: 163584 - EOS ID: 163585
Traceback (most recent call last):
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 5112, in <module>
    main()
    ~~~~^^
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 5102, in main
    model_instance.write_vocab()
    ~~~~~~~~~~~~~~~~~~~~~~~~~~^^
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 450, in write_vocab
    self.prepare_metadata(vocab_only=False)
    ~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 433, in prepare_metadata
    self.set_vocab()
    ~~~~~~~~~~~~~~^^
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 4058, in set_vocab
    self._set_vocab_gpt2()
    ~~~~~~~~~~~~~~~~~~~~^^
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 728, in _set_vocab_gpt2
    tokens, toktypes, tokpre = self.get_vocab_base()
                               ~~~~~~~~~~~~~~~~~~~^^
  File "/home/me/llama.cpp/convert_hf_to_gguf.py", line 523, in get_vocab_base
    vocab_size = self.hparams.get("vocab_size", len(tokenizer.vocab))
                                                    ^^^^^^^^^^^^^^^
  File "/home/me/llama.cpp/venv/lib/python3.13/site-packages/transformers/tokenization_utils_base.py", line 1108, in __getattr__
    raise AttributeError(f"{self.__class__.__name__} has no attribute {key}")
AttributeError: TikTokenTokenizer has no attribute vocab

Do you know how to fix this?
Thanks!

grapevine-AI

Feb 23, 2025

You should use tokenizer.vocab_size instead of len(tokenizer.vocab)

Doctor-Chad-PhD

Feb 23, 2025

Thank you @grapevine-AI , it works now!

toothacher17

Feb 24, 2025

Thanks @grapevine-AI for the help! I'll close this issue since it is fixed

toothacher17 changed discussion status to closed Feb 24, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment