MiniCPM5-1B-AutoRound-MXFP4-RTN

Model Details

This model is a MXFP4 (Microscaling FP4) quantization of openbmb/MiniCPM5-1B generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	openbmb/MiniCPM5-1B
Quantization Tool	AutoRound
Quantization Scheme	MXFP4
Original Size	1089 MB
Quantized Size	1347 MB

Evaluation Results

Task	Accuracy
hellaswag	0.3533
mmlu	0.4351
mmlu_abstract_algebra	0.2500
mmlu_anatomy	0.4593
mmlu_astronomy	0.4605
mmlu_business_ethics	0.3800
mmlu_clinical_knowledge	0.5509
mmlu_college_biology	0.4306
mmlu_college_chemistry	0.3400
mmlu_college_computer_science	0.3000
mmlu_college_mathematics	0.2500
mmlu_college_medicine	0.4104
mmlu_college_physics	0.2255
mmlu_computer_security	0.5000
mmlu_conceptual_physics	0.3830
mmlu_econometrics	0.3158
mmlu_electrical_engineering	0.4897
mmlu_elementary_mathematics	0.3492
mmlu_formal_logic	0.3016
mmlu_global_facts	0.3100
mmlu_high_school_biology	0.4742
mmlu_high_school_chemistry	0.3842
mmlu_high_school_computer_science	0.3900
mmlu_high_school_european_history	0.5273
mmlu_high_school_geography	0.5455
mmlu_high_school_government_and_politics	0.5130
mmlu_high_school_macroeconomics	0.4231
mmlu_high_school_mathematics	0.2667
mmlu_high_school_microeconomics	0.4580
mmlu_high_school_physics	0.2185
mmlu_high_school_psychology	0.5505
mmlu_high_school_statistics	0.3519
mmlu_high_school_us_history	0.4461
mmlu_high_school_world_history	0.5570
mmlu_human_aging	0.4933
mmlu_human_sexuality	0.5649
mmlu_humanities	0.3930
mmlu_international_law	0.6612
mmlu_jurisprudence	0.5556
mmlu_logical_fallacies	0.5399
mmlu_machine_learning	0.3661
mmlu_management	0.5631
mmlu_marketing	0.6709
mmlu_medical_genetics	0.5600
mmlu_miscellaneous	0.6028
mmlu_moral_disputes	0.4538
mmlu_moral_scenarios	0.2313
mmlu_nutrition	0.5327
mmlu_other	0.5108
mmlu_philosophy	0.4855
mmlu_prehistory	0.4167
mmlu_professional_accounting	0.3723
mmlu_professional_law	0.3462
mmlu_professional_medicine	0.4007
mmlu_professional_psychology	0.4101
mmlu_public_relations	0.5000
mmlu_security_studies	0.5184
mmlu_social_sciences	0.4917
mmlu_sociology	0.6269
mmlu_stem	0.3679
mmlu_us_foreign_policy	0.6300
mmlu_virology	0.4277
mmlu_world_religions	0.5380
piqa	0.6377

How to Use

HF Usage

Step 1: Install AutoRound

pip install auto-round

Step 2: Load and run the quantized model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "MiniCPM5-1B-AutoRound-MXFP4-RTN"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")

# prepare the model input
prompt = "Write a quick sort algorithm."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(**model_inputs, max_new_tokens=512)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist()

content = tokenizer.decode(output_ids, skip_special_tokens=True)
print("content:", content)

VLLM Usage

vllm serve MiniCPM5-1B-AutoRound-MXFP4-RTN \
    --trust-remote-code \
    --dtype bfloat16 \
    --tensor_parallel_size 1

If you encounter any issues, feel free to open an issue on the AutoRound GitHub repo or provide feedback on the Low-Bit Open LLM Leaderboard.

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:

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

This model is part of the Intel Low-Bit Open LLM Leaderboard initiative.