Instructions to use yujiepan/kimi-k3-bf16-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/kimi-k3-bf16-tiny-random with Transformers:

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

pipe = pipeline("image-text-to-text", model="yujiepan/kimi-k3-bf16-tiny-random", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("yujiepan/kimi-k3-bf16-tiny-random", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yujiepan/kimi-k3-bf16-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/kimi-k3-bf16-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/kimi-k3-bf16-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yujiepan/kimi-k3-bf16-tiny-random

SGLang

How to use yujiepan/kimi-k3-bf16-tiny-random 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 "yujiepan/kimi-k3-bf16-tiny-random" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/kimi-k3-bf16-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "yujiepan/kimi-k3-bf16-tiny-random" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/kimi-k3-bf16-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yujiepan/kimi-k3-bf16-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/kimi-k3-bf16-tiny-random
```

kimi-k3-bf16-tiny-random / preprocessor_config.json

yujiepan

Upload folder using huggingface_hub

2063170 verified 5 days ago

Raw

History Blame Contribute Delete

1.01 kB

	{
	"media_proc_cfg": {
	"in_patch_limit": 65536,
	"patch_size": 14,
	"image_mean": [
	0.5,
	0.5,
	0.5
	],
	"image_std": [
	0.5,
	0.5,
	0.5
	],
	"merge_kernel_size": 2,
	"fixed_output_tokens": null,
	"patch_limit_on_one_side": 512,
	"in_patch_limit_each_frame": 16384,
	"in_patch_limit_video": 655360,
	"sample_fps": 8.0,
	"max_num_frames_each_video": null,
	"temporal_merge_kernel_size": 4,
	"timestamp_mode": "hh:mm:ss.fff",
	"transparent_bg_config": {
	"pattern": "chessboard",
	"chessboard_square_size": 8,
	"chessboard_square_on_top_left": true,
	"chessboard_white_value": 255,
	"chessboard_gray_value": 180
	},
	"transparent_bg_fill_stage": "after_resize",
	"config_type": "media_proc.processors.moonvit.MoonViTMediaProcessorConfig"
	},
	"auto_map": {
	"AutoProcessor": "kimi_k3_processor.KimiK3Processor",
	"AutoImageProcessor": "kimi_k3_vision_processing.KimiK3VisionProcessor"
	}
	}