This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of Jackrong/Qwopus3.6-27B-v2 generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	Jackrong/Qwopus3.6-27B-v2
Quantization Tool	AutoRound
Quantization Scheme	W4A16
Quantized Size	18117 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6384
mmlu	0.8440
mmlu_abstract_algebra	0.7100
mmlu_anatomy	0.8148
mmlu_astronomy	0.9408
mmlu_business_ethics	0.8100
mmlu_clinical_knowledge	0.8868
mmlu_college_biology	0.9444
mmlu_college_chemistry	0.6800
mmlu_college_computer_science	0.8200
mmlu_college_mathematics	0.7600
mmlu_college_medicine	0.8613
mmlu_college_physics	0.7451
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.8638
mmlu_econometrics	0.7632
mmlu_electrical_engineering	0.7931
mmlu_elementary_mathematics	0.8862
mmlu_formal_logic	0.7778
mmlu_global_facts	0.6200
mmlu_high_school_biology	0.9419
mmlu_high_school_chemistry	0.8276
mmlu_high_school_computer_science	0.9300
mmlu_high_school_european_history	0.8970
mmlu_high_school_geography	0.9394
mmlu_high_school_government_and_politics	0.9585
mmlu_high_school_macroeconomics	0.9128
mmlu_high_school_mathematics	0.6444
mmlu_high_school_microeconomics	0.9496
mmlu_high_school_physics	0.8212
mmlu_high_school_psychology	0.9339
mmlu_high_school_statistics	0.8611
mmlu_high_school_us_history	0.9412
mmlu_high_school_world_history	0.9578
mmlu_human_aging	0.8117
mmlu_human_sexuality	0.9160
mmlu_humanities	0.8002
mmlu_international_law	0.9256
mmlu_jurisprudence	0.8796
mmlu_logical_fallacies	0.9264
mmlu_machine_learning	0.7500
mmlu_management	0.8447
mmlu_marketing	0.9444
mmlu_medical_genetics	0.9200
mmlu_miscellaneous	0.9387
mmlu_moral_disputes	0.7746
mmlu_moral_scenarios	0.7486
mmlu_nutrition	0.9052
mmlu_other	0.8674
mmlu_philosophy	0.7813
mmlu_prehistory	0.9167
mmlu_professional_accounting	0.8050
mmlu_professional_law	0.7249
mmlu_professional_medicine	0.9338
mmlu_professional_psychology	0.8742
mmlu_public_relations	0.7909
mmlu_security_studies	0.8204
mmlu_social_sciences	0.8999
mmlu_sociology	0.9254
mmlu_stem	0.8316
mmlu_us_foreign_policy	0.9100
mmlu_virology	0.5663
mmlu_world_religions	0.8889
piqa	0.8215

How to Use

HF Usage

Step 1: Install AutoRound

pip install auto-round

Step 2: Load and run the quantized model

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwopus3.6-27B-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

bash

vllm serve Qwopus3.6-27B-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.

LeaderboardModel1/Qwopus3.6-27B-v2-AutoRound-W4A16-RTN

Qwopus3.6-27B-v2-AutoRound-W4A16-RTN

Model Details