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

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 TUNING. Please follow the license of the original model.

Quantization Details

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

Evaluation Results

Task	Accuracy
hellaswag	0.6266
mmlu	0.7971
mmlu_abstract_algebra	0.5900
mmlu_anatomy	0.8444
mmlu_astronomy	0.9276
mmlu_business_ethics	0.8200
mmlu_clinical_knowledge	0.9019
mmlu_college_biology	0.9375
mmlu_college_chemistry	0.6000
mmlu_college_computer_science	0.7500
mmlu_college_mathematics	0.6200
mmlu_college_medicine	0.8266
mmlu_college_physics	0.7059
mmlu_computer_security	0.8700
mmlu_conceptual_physics	0.9191
mmlu_econometrics	0.7456
mmlu_electrical_engineering	0.8345
mmlu_elementary_mathematics	0.8201
mmlu_formal_logic	0.6587
mmlu_global_facts	0.5300
mmlu_high_school_biology	0.9484
mmlu_high_school_chemistry	0.7833
mmlu_high_school_computer_science	0.9100
mmlu_high_school_european_history	0.8667
mmlu_high_school_geography	0.9394
mmlu_high_school_government_and_politics	0.9637
mmlu_high_school_macroeconomics	0.8923
mmlu_high_school_mathematics	0.5815
mmlu_high_school_microeconomics	0.9622
mmlu_high_school_physics	0.7682
mmlu_high_school_psychology	0.9523
mmlu_high_school_statistics	0.7731
mmlu_high_school_us_history	0.9118
mmlu_high_school_world_history	0.8776
mmlu_human_aging	0.8206
mmlu_human_sexuality	0.8626
mmlu_humanities	0.6950
mmlu_international_law	0.9091
mmlu_jurisprudence	0.8426
mmlu_logical_fallacies	0.9386
mmlu_machine_learning	0.7589
mmlu_management	0.8932
mmlu_marketing	0.9444
mmlu_medical_genetics	0.9400
mmlu_miscellaneous	0.9323
mmlu_moral_disputes	0.8526
mmlu_moral_scenarios	0.3162
mmlu_nutrition	0.8791
mmlu_other	0.8526
mmlu_philosophy	0.8360
mmlu_prehistory	0.8981
mmlu_professional_accounting	0.7340
mmlu_professional_law	0.6584
mmlu_professional_medicine	0.8971
mmlu_professional_psychology	0.8676
mmlu_public_relations	0.7091
mmlu_security_studies	0.8163
mmlu_social_sciences	0.8947
mmlu_sociology	0.9154
mmlu_stem	0.7996
mmlu_us_foreign_policy	0.9400
mmlu_virology	0.5542
mmlu_world_religions	0.9181
piqa	0.8128

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-Tuning"

# 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-Tuning \
    --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.