Instructions to use win10/K1-v6-zero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use win10/K1-v6-zero with Transformers:

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

pipe = pipeline("text-generation", model="win10/K1-v6-zero")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("win10/K1-v6-zero")
model = AutoModelForImageTextToText.from_pretrained("win10/K1-v6-zero")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use win10/K1-v6-zero with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "win10/K1-v6-zero"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "win10/K1-v6-zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/win10/K1-v6-zero

SGLang

How to use win10/K1-v6-zero 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 "win10/K1-v6-zero" \
    --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": "win10/K1-v6-zero",
		"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 "win10/K1-v6-zero" \
        --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": "win10/K1-v6-zero",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use win10/K1-v6-zero with Docker Model Runner:
```
docker model run hf.co/win10/K1-v6-zero
```

K1-v6-zero / README.md

win10

Create README.md

4822136 verified 1 day ago

preview code

raw

history blame contribute delete

470 Bytes

metadata

license: apache-2.0
datasets:
  - stepfun-ai/Step-3.5-Flash-SFT
  - ianncity/KIMI-K2.5-1000000x
language:
  - zh
  - en
base_model:
  - huihui-ai/Huihui-gemma-4-31B-it-abliterated
pipeline_tag: text-generation
library_name: transformers
tags:
  - RL
  - text-generation-inference
  - Gemma4
  - grpo
  - r1-zero

This is an experimental model trained with SFT and GRPO-ZERO, and it comes with absolutely no guarantee that it won’t break, collapse, or otherwise fail spectacularly.