Instructions to use moonshotai/Kimi-Dev-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-Dev-72B with Transformers:

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

pipe = pipeline("text-generation", model="moonshotai/Kimi-Dev-72B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("moonshotai/Kimi-Dev-72B")
model = AutoModelForCausalLM.from_pretrained("moonshotai/Kimi-Dev-72B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use moonshotai/Kimi-Dev-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-Dev-72B"
# 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/Kimi-Dev-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moonshotai/Kimi-Dev-72B

SGLang

How to use moonshotai/Kimi-Dev-72B 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/Kimi-Dev-72B" \
    --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/Kimi-Dev-72B",
		"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/Kimi-Dev-72B" \
        --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/Kimi-Dev-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use moonshotai/Kimi-Dev-72B with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-Dev-72B
```

Add converted tokenizer (no trust_remote_code needed)

#12

by ArthurZ HF Staff - opened Feb 6

base: refs/heads/main

←

from: refs/pr/12

Discussion Files changed

+66

-303468

ArthurZ

Feb 6

Tokenizer Conversion

This PR adds a converted tokenizer that works without trust_remote_code=True.

Conversion Details

Converted using: python scripts/convert_tokenizer.py moonshotai/Kimi-Dev-72B --push-to-hub
Original tokenizer type: Qwen2Tokenizer
Converted tokenizer type: Qwen2Tokenizer

Validation Results

Tested on XNLI dataset (500 samples)
All samples match 1-1 ✓

Usage

from transformers import AutoTokenizer

# Now works without trust_remote_code=True
tokenizer = AutoTokenizer.from_pretrained("moonshotai/Kimi-Dev-72B")

Converted with transformers tokenizer conversion script

Add converted tokenizer (no trust_remote_code needed)851a6a3b

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment