Ornith-1.0-35B-uncensored-heretic-AutoRound-W4A16-RTN

Model Details

This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of llmfan46/Ornith-1.0-35B-uncensored-heretic generated by AutoRound. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	llmfan46/Ornith-1.0-35B-uncensored-heretic
Quantization Tool	AutoRound
Quantization Scheme	W4A16
Quantized Size	19504 MB

Evaluation Results

Task	Accuracy
hellaswag	0.6334
mmlu	0.8010
mmlu_abstract_algebra	0.5600
mmlu_anatomy	0.8296
mmlu_astronomy	0.9013
mmlu_business_ethics	0.8200
mmlu_clinical_knowledge	0.8981
mmlu_college_biology	0.9306
mmlu_college_chemistry	0.6100
mmlu_college_computer_science	0.7300
mmlu_college_mathematics	0.6100
mmlu_college_medicine	0.8324
mmlu_college_physics	0.6961
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.9277
mmlu_econometrics	0.7982
mmlu_electrical_engineering	0.8276
mmlu_elementary_mathematics	0.8333
mmlu_formal_logic	0.6905
mmlu_global_facts	0.5000
mmlu_high_school_biology	0.9355
mmlu_high_school_chemistry	0.8079
mmlu_high_school_computer_science	0.9000
mmlu_high_school_european_history	0.8485
mmlu_high_school_geography	0.9394
mmlu_high_school_government_and_politics	0.9637
mmlu_high_school_macroeconomics	0.8872
mmlu_high_school_mathematics	0.6111
mmlu_high_school_microeconomics	0.9622
mmlu_high_school_physics	0.8079
mmlu_high_school_psychology	0.9468
mmlu_high_school_statistics	0.7685
mmlu_high_school_us_history	0.9118
mmlu_high_school_world_history	0.8945
mmlu_human_aging	0.8251
mmlu_human_sexuality	0.8779
mmlu_humanities	0.7012
mmlu_international_law	0.9008
mmlu_jurisprudence	0.8704
mmlu_logical_fallacies	0.9018
mmlu_machine_learning	0.7411
mmlu_management	0.9029
mmlu_marketing	0.9658
mmlu_medical_genetics	0.9400
mmlu_miscellaneous	0.9298
mmlu_moral_disputes	0.8439
mmlu_moral_scenarios	0.3944
mmlu_nutrition	0.8693
mmlu_other	0.8542
mmlu_philosophy	0.8457
mmlu_prehistory	0.9012
mmlu_professional_accounting	0.7305
mmlu_professional_law	0.6310
mmlu_professional_medicine	0.9154
mmlu_professional_psychology	0.8775
mmlu_public_relations	0.7364
mmlu_security_studies	0.8408
mmlu_social_sciences	0.9006
mmlu_sociology	0.9055
mmlu_stem	0.8005
mmlu_us_foreign_policy	0.9600
mmlu_virology	0.5663
mmlu_world_religions	0.9123
piqa	0.8145

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-1.0-35B-uncensored-heretic-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 Ornith-1.0-35B-uncensored-heretic-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.