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

Quantization Details

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

Evaluation Results

Task	Accuracy
hellaswag	0.6358
mmlu	0.8503
mmlu_abstract_algebra	0.7000
mmlu_anatomy	0.8593
mmlu_astronomy	0.9539
mmlu_business_ethics	0.8300
mmlu_clinical_knowledge	0.9057
mmlu_college_biology	0.9653
mmlu_college_chemistry	0.6400
mmlu_college_computer_science	0.8200
mmlu_college_mathematics	0.7800
mmlu_college_medicine	0.8671
mmlu_college_physics	0.7059
mmlu_computer_security	0.8800
mmlu_conceptual_physics	0.9021
mmlu_econometrics	0.7807
mmlu_electrical_engineering	0.8414
mmlu_elementary_mathematics	0.8677
mmlu_formal_logic	0.7778
mmlu_global_facts	0.6000
mmlu_high_school_biology	0.9452
mmlu_high_school_chemistry	0.8276
mmlu_high_school_computer_science	0.9400
mmlu_high_school_european_history	0.9030
mmlu_high_school_geography	0.9495
mmlu_high_school_government_and_politics	0.9845
mmlu_high_school_macroeconomics	0.9282
mmlu_high_school_mathematics	0.6481
mmlu_high_school_microeconomics	0.9664
mmlu_high_school_physics	0.8013
mmlu_high_school_psychology	0.9560
mmlu_high_school_statistics	0.8657
mmlu_high_school_us_history	0.9461
mmlu_high_school_world_history	0.9578
mmlu_human_aging	0.8475
mmlu_human_sexuality	0.9313
mmlu_humanities	0.8017
mmlu_international_law	0.9256
mmlu_jurisprudence	0.9074
mmlu_logical_fallacies	0.9325
mmlu_machine_learning	0.7589
mmlu_management	0.8835
mmlu_marketing	0.9487
mmlu_medical_genetics	0.9500
mmlu_miscellaneous	0.9374
mmlu_moral_disputes	0.7919
mmlu_moral_scenarios	0.7385
mmlu_nutrition	0.9118
mmlu_other	0.8748
mmlu_philosophy	0.8392
mmlu_prehistory	0.9136
mmlu_professional_accounting	0.8050
mmlu_professional_law	0.7145
mmlu_professional_medicine	0.9522
mmlu_professional_psychology	0.8807
mmlu_public_relations	0.8000
mmlu_security_studies	0.8204
mmlu_social_sciences	0.9136
mmlu_sociology	0.9353
mmlu_stem	0.8370
mmlu_us_foreign_policy	0.9300
mmlu_virology	0.5361
mmlu_world_religions	0.9064
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-Coder-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-Coder-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-Coder-AutoRound-W4A16-RTN

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

Model Details