Instructions to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound with Transformers:

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

pipe = pipeline("image-text-to-text", model="INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound", trust_remote_code=True)
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("INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound", trust_remote_code=True)
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 INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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/INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound

SGLang

How to use INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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 "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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 "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-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 INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound with Docker Model Runner:
```
docker model run hf.co/INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound
```

MiniMax-M3-MXFP4-Mixed-CT-AutoRound / README.md

lvkaokao

Update README.md

ee66df8 verified 2 days ago

preview code

Raw

History Blame Contribute Delete

3.28 kB

metadata

pipeline_tag: image-text-to-text
license: other
license_name: minimax-community
license_link: LICENSE
library_name: transformers
tags:
  - multimodal
  - moe
  - agent
  - coding
  - video

This model is a MXFP4 mixed model of MiniMax-M3 generated by intel/auto-round with llm_compressor format. Please follow the license of the original model.

MOE (block_sparse_moe.experts): MXFP4
MOE (block_sparse_moe.shared_experts): MXFP8

Configuration	GSM8K	MMLU	PIQA	HelleSwag	Average	Relative to BF16
BF16	95.30	0.8415	0.8259	0.6714	0.82295	-
MXFP4 (experts) + MXFP8 (shared_experts)	95.30	0.8282	0.8237	0.6528	0.814425	98.96%

How to Run Locally

vllm serve \
  INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound \
  --tensor-parallel-size 2 \
  --max-model-len 131072 \
  --tool-call-parser minimax_m3 \
  --reasoning-parser minimax_m3 \
  --enable-auto-tool-choice \
  --port 8000

curl -s http://127.0.0.1:8000/v1/chat/completions   -H "Content-Type: application/json"   -d '{
    "model": "INCModelSharing/MiniMax-M3-MXFP4-Mixed-CT-AutoRound",
    "messages": [
      {"role":"user","content":"2+3=?"}
    ],
    "max_tokens": 10,
    "extra_body": {
      "chat_template_kwargs": {
        "enable_thinking": true
      }
    }
  }' | python3 -m json.tool

Generate the Model

auto-round MiniMaxAI/MiniMax-M3 --model_free \
  --scheme MXFP8 \
  --ignore_layers vision_tower,lm_head,block_sparse_moe.gate,embed_tokens,self_attn,\
patch_merge_mlp,multi_modal_projector,mlp.gate_proj,mlp.up_proj,mlp.down_proj \
  --layer_config "{block_sparse_moe.experts:{bits:4,data_type:mx_fp}}" \
  --format llm_compressor \
  --output_dir "./MiniMax-M3-MXFP4-Mixed-CT-AutoRound"

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