Instructions to use Zaynoid/Kimi-K2-Thinking-Tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zaynoid/Kimi-K2-Thinking-Tokenizer with Transformers:

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

pipe = pipeline("text-generation", model="Zaynoid/Kimi-K2-Thinking-Tokenizer", 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("Zaynoid/Kimi-K2-Thinking-Tokenizer", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Zaynoid/Kimi-K2-Thinking-Tokenizer", 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 Zaynoid/Kimi-K2-Thinking-Tokenizer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zaynoid/Kimi-K2-Thinking-Tokenizer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zaynoid/Kimi-K2-Thinking-Tokenizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zaynoid/Kimi-K2-Thinking-Tokenizer

SGLang

How to use Zaynoid/Kimi-K2-Thinking-Tokenizer 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 "Zaynoid/Kimi-K2-Thinking-Tokenizer" \
    --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": "Zaynoid/Kimi-K2-Thinking-Tokenizer",
		"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 "Zaynoid/Kimi-K2-Thinking-Tokenizer" \
        --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": "Zaynoid/Kimi-K2-Thinking-Tokenizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zaynoid/Kimi-K2-Thinking-Tokenizer with Docker Model Runner:
```
docker model run hf.co/Zaynoid/Kimi-K2-Thinking-Tokenizer
```

Configuration Parsing Warning:In UNKNOWN_FILENAME: "auto_map.AutoTokenizer" must be a string

Kimi-K2-Thinking Tokenizer

Tokenizer files for moonshotai/Kimi-K2-Thinking - a trillion-parameter thinking model.

📦 What's Included

tiktoken.model - Original tiktoken tokenizer (2.8MB)
tokenizer.json - HuggingFace compatible format
tokenization_kimi.py - Custom tokenization code
tokenizer_config.json - Configuration
special_tokens_map.json - Special tokens
chat_template.jinja - Chat template

🚀 Quick Start

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "Zaynoid/Kimi-K2-Thinking-Tokenizer",
    trust_remote_code=True
)

text = "Hello, how are you?"
tokens = tokenizer.encode(text)
print(f"Tokens: {tokens}")
print(f"Decoded: {tokenizer.decode(tokens)}")

📊 Specifications

Vocab Size: 163,840 tokens
Model Type: Tiktoken (BPE-based)
Context Length: 256K tokens
Special Tokens:
- BOS: <｜begin▁of▁sentence｜> (ID: 163584)
- EOS: <｜end▁of▁sentence｜> (ID: 163585)

💡 Usage Notes

Recommended: Use with trust_remote_code=True for full compatibility
The tokenizer.json is provided for tools that require it
Original model uses tiktoken format natively

🔧 Use with vLLM

from vllm import LLM

llm = LLM(
    model="moonshotai/Kimi-K2-Thinking",
    tokenizer="Zaynoid/Kimi-K2-Thinking-Tokenizer",
    trust_remote_code=True
)

📝 License

Modified MIT License (same as base model)

🙏 Credits

Original Model: Moonshot AI
Architecture: Based on DeepSeek-V3
Tokenizer Extraction: Zaynoid

🔗 Links

Downloads last month: 19

Model tree for Zaynoid/Kimi-K2-Thinking-Tokenizer

Base model

moonshotai/Kimi-K2-Thinking

Finetuned

(14)

this model