Qwythos-9B-v2-AutoRound-W4A16-RTN

Model Details

This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of empero-ai/Qwythos-9B-v2 generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	empero-ai/Qwythos-9B-v2
Quantization Tool	AutoRound
Quantization Scheme	W4A16
Quantized Size	8348 MB

Evaluation Results

Task	Accuracy
hellaswag	0.5730
mmlu	0.7648
mmlu_abstract_algebra	0.6100
mmlu_anatomy	0.7778
mmlu_astronomy	0.9276
mmlu_business_ethics	0.8000
mmlu_clinical_knowledge	0.8264
mmlu_college_biology	0.9028
mmlu_college_chemistry	0.6200
mmlu_college_computer_science	0.7800
mmlu_college_mathematics	0.6100
mmlu_college_medicine	0.8266
mmlu_college_physics	0.6471
mmlu_computer_security	0.8400
mmlu_conceptual_physics	0.8638
mmlu_econometrics	0.6930
mmlu_electrical_engineering	0.7793
mmlu_elementary_mathematics	0.7804
mmlu_formal_logic	0.6349
mmlu_global_facts	0.4100
mmlu_high_school_biology	0.9323
mmlu_high_school_chemistry	0.7783
mmlu_high_school_computer_science	0.8600
mmlu_high_school_european_history	0.8667
mmlu_high_school_geography	0.9293
mmlu_high_school_government_and_politics	0.9534
mmlu_high_school_macroeconomics	0.8436
mmlu_high_school_mathematics	0.5222
mmlu_high_school_microeconomics	0.9202
mmlu_high_school_physics	0.7152
mmlu_high_school_psychology	0.9211
mmlu_high_school_statistics	0.7731
mmlu_high_school_us_history	0.8922
mmlu_high_school_world_history	0.9072
mmlu_human_aging	0.7892
mmlu_human_sexuality	0.8550
mmlu_humanities	0.6704
mmlu_international_law	0.8430
mmlu_jurisprudence	0.8611
mmlu_logical_fallacies	0.8405
mmlu_machine_learning	0.6518
mmlu_management	0.8544
mmlu_marketing	0.9274
mmlu_medical_genetics	0.8900
mmlu_miscellaneous	0.8838
mmlu_moral_disputes	0.7775
mmlu_moral_scenarios	0.4547
mmlu_nutrition	0.8464
mmlu_other	0.8098
mmlu_philosophy	0.7878
mmlu_prehistory	0.8148
mmlu_professional_accounting	0.6241
mmlu_professional_law	0.5671
mmlu_professional_medicine	0.8934
mmlu_professional_psychology	0.8154
mmlu_public_relations	0.7091
mmlu_security_studies	0.7633
mmlu_social_sciences	0.8609
mmlu_sociology	0.9254
mmlu_stem	0.7678
mmlu_us_foreign_policy	0.9000
mmlu_virology	0.5602
mmlu_world_religions	0.8596
piqa	0.7894

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 = "Qwythos-9B-v2-AutoRound-W4A16-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 Qwythos-9B-v2-AutoRound-W4A16-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.