Instructions to use aciklab/kubernetes-ai-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aciklab/kubernetes-ai-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="aciklab/kubernetes-ai-4bit")
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("aciklab/kubernetes-ai-4bit")
model = AutoModelForImageTextToText.from_pretrained("aciklab/kubernetes-ai-4bit")
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 aciklab/kubernetes-ai-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aciklab/kubernetes-ai-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aciklab/kubernetes-ai-4bit",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/aciklab/kubernetes-ai-4bit

SGLang

How to use aciklab/kubernetes-ai-4bit 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 "aciklab/kubernetes-ai-4bit" \
    --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": "aciklab/kubernetes-ai-4bit",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "aciklab/kubernetes-ai-4bit" \
        --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": "aciklab/kubernetes-ai-4bit",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use aciklab/kubernetes-ai-4bit with Docker Model Runner:
```
docker model run hf.co/aciklab/kubernetes-ai-4bit
```

kubernetes-ai-4bit / config.json

ikaganacar

Upload folder using huggingface_hub

62dcb9c verified 8 months ago

raw

history blame contribute delete

3.53 kB

	{
	"architectures": [
	"Gemma3ForConditionalGeneration"
	],
	"boi_token_index": 255999,
	"bos_token_id": 2,
	"eoi_token_index": 256000,
	"eos_token_id": 106,
	"image_token_index": 262144,
	"initializer_range": 0.02,
	"mm_tokens_per_image": 256,
	"model_type": "gemma3",
	"pad_token_id": 0,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": true,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": [
	"lm_head",
	"multi_modal_projector",
	"merger",
	"modality_projection"
	],
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"text_config": {
	"_sliding_window_pattern": 6,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": null,
	"cache_implementation": "hybrid",
	"final_logit_softcapping": null,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 3840,
	"initializer_range": 0.02,
	"intermediate_size": 15360,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 131072,
	"model_type": "gemma3_text",
	"num_attention_heads": 16,
	"num_hidden_layers": 48,
	"num_key_value_heads": 8,
	"query_pre_attn_scalar": 256,
	"rms_norm_eps": 1e-06,
	"rope_local_base_freq": 10000,
	"rope_scaling": {
	"factor": 8.0,
	"rope_type": "linear"
	},
	"rope_theta": 1000000,
	"sliding_window": 1024,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"vocab_size": 262208
	},
	"torch_dtype": "bfloat16",
	"transformers_version": "4.55.4",
	"unsloth_fixed": true,
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"image_size": 896,
	"intermediate_size": 4304,
	"layer_norm_eps": 1e-06,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"patch_size": 14,
	"torch_dtype": "bfloat16",
	"vision_use_head": false
	}
	}