Ornith-1.0-9B-AutoRound-W4A16-Tuning

Model Details

This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of deepreinforce-ai/Ornith-1.0-9B generated by TUNING. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	deepreinforce-ai/Ornith-1.0-9B
Quantization Tool	TUNING
Quantization Scheme	W4A16
Quantized Size	8180 MB

Evaluation Results

Task	Accuracy
hellaswag	0.5827
mmlu	0.7758
mmlu_abstract_algebra	0.6200
mmlu_anatomy	0.7481
mmlu_astronomy	0.9013
mmlu_business_ethics	0.7900
mmlu_clinical_knowledge	0.8528
mmlu_college_biology	0.9375
mmlu_college_chemistry	0.6000
mmlu_college_computer_science	0.7600
mmlu_college_mathematics	0.5900
mmlu_college_medicine	0.8092
mmlu_college_physics	0.6373
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.8936
mmlu_econometrics	0.6842
mmlu_electrical_engineering	0.8000
mmlu_elementary_mathematics	0.7751
mmlu_formal_logic	0.6190
mmlu_global_facts	0.5200
mmlu_high_school_biology	0.9419
mmlu_high_school_chemistry	0.7783
mmlu_high_school_computer_science	0.8700
mmlu_high_school_european_history	0.8788
mmlu_high_school_geography	0.9141
mmlu_high_school_government_and_politics	0.9637
mmlu_high_school_macroeconomics	0.8641
mmlu_high_school_mathematics	0.5407
mmlu_high_school_microeconomics	0.9160
mmlu_high_school_physics	0.6821
mmlu_high_school_psychology	0.9248
mmlu_high_school_statistics	0.7500
mmlu_high_school_us_history	0.8922
mmlu_high_school_world_history	0.9198
mmlu_human_aging	0.7668
mmlu_human_sexuality	0.8473
mmlu_humanities	0.6976
mmlu_international_law	0.8843
mmlu_jurisprudence	0.8333
mmlu_logical_fallacies	0.8528
mmlu_machine_learning	0.6607
mmlu_management	0.8447
mmlu_marketing	0.9231
mmlu_medical_genetics	0.8900
mmlu_miscellaneous	0.8863
mmlu_moral_disputes	0.7890
mmlu_moral_scenarios	0.5318
mmlu_nutrition	0.8464
mmlu_other	0.8133
mmlu_philosophy	0.7910
mmlu_prehistory	0.8457
mmlu_professional_accounting	0.6489
mmlu_professional_law	0.5919
mmlu_professional_medicine	0.8860
mmlu_professional_psychology	0.8219
mmlu_public_relations	0.7364
mmlu_security_studies	0.7878
mmlu_social_sciences	0.8655
mmlu_sociology	0.8905
mmlu_stem	0.7682
mmlu_us_foreign_policy	0.9200
mmlu_virology	0.5422
mmlu_world_religions	0.8538
piqa	0.7845

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 = "Ornith-1.0-9B-AutoRound-W4A16-Tuning"

# 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 Ornith-1.0-9B-AutoRound-W4A16-Tuning \
    --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:

• Intel Neural Compressor
• AutoRound

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.