Instructions to use SLBM/affine-k100-king-head with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SLBM/affine-k100-king-head with Transformers:

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

pipe = pipeline("text-generation", model="SLBM/affine-k100-king-head")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SLBM/affine-k100-king-head")
model = AutoModelForMultimodalLM.from_pretrained("SLBM/affine-k100-king-head", device_map="auto")
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 Settings

vLLM

How to use SLBM/affine-k100-king-head with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SLBM/affine-k100-king-head"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SLBM/affine-k100-king-head",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SLBM/affine-k100-king-head

SGLang

How to use SLBM/affine-k100-king-head 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 "SLBM/affine-k100-king-head" \
    --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": "SLBM/affine-k100-king-head",
		"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 "SLBM/affine-k100-king-head" \
        --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": "SLBM/affine-k100-king-head",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SLBM/affine-k100-king-head with Docker Model Runner:
```
docker model run hf.co/SLBM/affine-k100-king-head
```

affine-k100-king-head

Private eval candidate. Not submitted to SN120.

Recipe: hv4 attention + hv4 routers + 100% sitting-king expert FFNs + sitting-king embed_tokens / lm_head / final RMSNorm.

Parents:

controllers: angryaffine/Affine-5dhnrnxlw4-hv4 @ 9116967529160659279f25bda30e8cfde26439cf
experts + vocab head: tojointhecommunity/affine-5efg6cm3yl-king @ 7c1c94cd0572475d4b3e3fde5258b0e79563d54f

Download:

huggingface-cli download SLBM/affine-k100-king-head --local-dir /workspace/models/soups/hv4_graft_king_experts_kinghead

Downloads last month: 284

Safetensors

Model size

35B params

Tensor type

BF16