Instructions to use INCModel2/Inkling-Small-MXFP4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use INCModel2/Inkling-Small-MXFP4-AutoRound with Transformers:

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

pipe = pipeline("image-text-to-text", model="INCModel2/Inkling-Small-MXFP4-AutoRound")
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("INCModel2/Inkling-Small-MXFP4-AutoRound")
model = AutoModelForMultimodalLM.from_pretrained("INCModel2/Inkling-Small-MXFP4-AutoRound", 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 INCModel2/Inkling-Small-MXFP4-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "INCModel2/Inkling-Small-MXFP4-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "INCModel2/Inkling-Small-MXFP4-AutoRound",
		"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/INCModel2/Inkling-Small-MXFP4-AutoRound

SGLang

How to use INCModel2/Inkling-Small-MXFP4-AutoRound 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 "INCModel2/Inkling-Small-MXFP4-AutoRound" \
    --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": "INCModel2/Inkling-Small-MXFP4-AutoRound",
		"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 "INCModel2/Inkling-Small-MXFP4-AutoRound" \
        --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": "INCModel2/Inkling-Small-MXFP4-AutoRound",
		"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 INCModel2/Inkling-Small-MXFP4-AutoRound with Docker Model Runner:
```
docker model run hf.co/INCModel2/Inkling-Small-MXFP4-AutoRound
```

Model Details

This model is a MXFP4 mixed model of thinkingmachines/Inkling-Small generated by intel/auto-round with RTN mode. Please follow the license of the original model.

Accuracy (repeats=3)	aime25	gpqa_diamond	gsm8k	piqa
thinkingmachines/Inkling-Small-NVFP4	0.9	0.8737	0.9727	0.9447
MXFP4	0.911	0.8855	0.9699	0.9452
Ratio	1.0123	1.0135	0.9971	1.0006

vllm Infernece Example

NCCL_NVLS_ENABLE=0  VLLM_QDQ=1 CUDA_VISIBLE_DEVICES=3,4,5,7 \
vllm serve ~/models/thinkingmachines/Inkling-Small-MXFP4  \
  --tokenizer-mode inkling  \
  --reasoning-parser inkling  \
  --tool-call-parser inkling  \
  --enable-auto-tool-choice  \
  --tensor-parallel-size 4  \
  --kernel-config.enable_flashinfer_autotune=False \
  --trust-remote-code  \
  --served-model-name mxfp \
  --max-model-len 102400 \
  --max-num-seqs 1024 \
  --max-num-batched-tokens 32768  \
  --enable-chunked-prefill \
 --port 8001

# Prompt generation
curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d ' {
    "model": "mxfp",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Write code to fine-tune an LLM."}
    ],
    "temperature": 1,
    "max_tokens": 2048
  } '

# Accuracy evaluation
evalscope eval   --model mxfp   --eval-type openai_api   --api-key EMPTY --timeout 36000  --datasets gpqa_diamond aime25 gsm8k piqa  \
 --generation-config  '{"temperature":1.0, "top_p":0.95,  "n":1, "extra_body": { "chat_template_kwargs": { "enable_thinking": true, "reasoning_effort": "max"}},"max_tokens":64000}' \
 --eval-batch-size 512 --api-url http://127.0.0.1:8001/v1

Generate the Model

RTN version

auto-round thinkingmachines/Inkling-Small --scheme BF16 --layer_config '{mlp.experts:{scheme:mxfp4}}' --output_dir ~/models/thinkingmachines/Inkling-Small-MXFP4  --model_free  --format llm_compressor

Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

Intel Neural Compressor

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

arxiv github