This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of osmapi/osmFableQwopus-3.6-27B-Uncensored generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	osmapi/osmFableQwopus-3.6-27B-Uncensored
Quantization Tool	AutoRound
Quantization Scheme	W4A16
Quantized Size	17832 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6453
mmlu	0.8504
mmlu_abstract_algebra	0.7800
mmlu_anatomy	0.8148
mmlu_astronomy	0.9342
mmlu_business_ethics	0.8400
mmlu_clinical_knowledge	0.9132
mmlu_college_biology	0.9514
mmlu_college_chemistry	0.6400
mmlu_college_computer_science	0.8500
mmlu_college_mathematics	0.7700
mmlu_college_medicine	0.8728
mmlu_college_physics	0.7353
mmlu_computer_security	0.8800
mmlu_conceptual_physics	0.9489
mmlu_econometrics	0.7895
mmlu_electrical_engineering	0.8414
mmlu_elementary_mathematics	0.8862
mmlu_formal_logic	0.7698
mmlu_global_facts	0.5700
mmlu_high_school_biology	0.9613
mmlu_high_school_chemistry	0.8374
mmlu_high_school_computer_science	0.9200
mmlu_high_school_european_history	0.8909
mmlu_high_school_geography	0.9394
mmlu_high_school_government_and_politics	0.9845
mmlu_high_school_macroeconomics	0.9359
mmlu_high_school_mathematics	0.6481
mmlu_high_school_microeconomics	0.9538
mmlu_high_school_physics	0.8146
mmlu_high_school_psychology	0.9505
mmlu_high_school_statistics	0.8611
mmlu_high_school_us_history	0.9461
mmlu_high_school_world_history	0.9494
mmlu_human_aging	0.8386
mmlu_human_sexuality	0.9313
mmlu_humanities	0.7962
mmlu_international_law	0.9339
mmlu_jurisprudence	0.9259
mmlu_logical_fallacies	0.8896
mmlu_machine_learning	0.8036
mmlu_management	0.8932
mmlu_marketing	0.9573
mmlu_medical_genetics	0.9400
mmlu_miscellaneous	0.9451
mmlu_moral_disputes	0.8324
mmlu_moral_scenarios	0.6927
mmlu_nutrition	0.9118
mmlu_other	0.8754
mmlu_philosophy	0.8714
mmlu_prehistory	0.9074
mmlu_professional_accounting	0.7908
mmlu_professional_law	0.7158
mmlu_professional_medicine	0.9412
mmlu_professional_psychology	0.8873
mmlu_public_relations	0.8091
mmlu_security_studies	0.8122
mmlu_social_sciences	0.9119
mmlu_sociology	0.9204
mmlu_stem	0.8468
mmlu_us_foreign_policy	0.9200
mmlu_virology	0.5482
mmlu_world_religions	0.9064
piqa	0.8194

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 = "osmFableQwopus-3.6-27B-Uncensored-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 osmFableQwopus-3.6-27B-Uncensored-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/osmFableQwopus-3.6-27B-Uncensored-AutoRound-W4A16-RTN

osmFableQwopus-3.6-27B-Uncensored-AutoRound-W4A16-RTN

Model Details