Instructions to use tiny-random/kimi-k2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/kimi-k2 with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/kimi-k2", 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("tiny-random/kimi-k2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiny-random/kimi-k2", 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 tiny-random/kimi-k2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/kimi-k2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/kimi-k2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/kimi-k2

SGLang

How to use tiny-random/kimi-k2 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 "tiny-random/kimi-k2" \
    --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": "tiny-random/kimi-k2",
		"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 "tiny-random/kimi-k2" \
        --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": "tiny-random/kimi-k2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/kimi-k2 with Docker Model Runner:
```
docker model run hf.co/tiny-random/kimi-k2
```

yujiepan commited on Jul 12, 2025

Commit

1bec50b

verified ·

1 Parent(s): 93c8028

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +2 -1
config.json +1 -0

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ This tiny model is for debugging. It is randomly initialized with the config ada
 - vLLM
 ```bash
-vllm serve tiny-random/kimi-k2
 ```
 - Transformers
@@ -94,6 +94,7 @@ config_json.update({
     'v_head_dim': 64,
     'tie_word_embeddings': False,
 })
 del config_json['quantization_config']
 with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
     json.dump(config_json, f, indent=2)

 - vLLM
 ```bash
+vllm serve tiny-random/kimi-k2 --trust-remote-code
 ```
 - Transformers
     'v_head_dim': 64,
     'tie_word_embeddings': False,
 })
+config_json['rope_scaling']['rope_type'] = 'yarn'
 del config_json['quantization_config']
 with open(f"{save_folder}/config.json", "w", encoding='utf-8') as f:
     json.dump(config_json, f, indent=2)

config.json CHANGED Viewed

@@ -44,6 +44,7 @@
     "mscale": 1.0,
     "mscale_all_dim": 1.0,
     "original_max_position_embeddings": 4096,
     "type": "yarn"
   },
   "rope_theta": 50000.0,

     "mscale": 1.0,
     "mscale_all_dim": 1.0,
     "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
     "type": "yarn"
   },
   "rope_theta": 50000.0,