This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of empero-ai/Qwythos-9B-Claude-Mythos-5-1M generated by TUNING. Please follow the license of the original model.

Quantization Details

Attribute	Value
Base Model	empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Quantization Tool	TUNING
Quantization Scheme	W4A16
Quantized Size	8180 MB

Evaluation Results

Task	Accuracy
hellaswag	0.5748
mmlu	0.7721
mmlu_abstract_algebra	0.6200
mmlu_anatomy	0.7704
mmlu_astronomy	0.9013
mmlu_business_ethics	0.8200
mmlu_clinical_knowledge	0.8453
mmlu_college_biology	0.9306
mmlu_college_chemistry	0.6000
mmlu_college_computer_science	0.7400
mmlu_college_mathematics	0.6200
mmlu_college_medicine	0.8035
mmlu_college_physics	0.6569
mmlu_computer_security	0.8600
mmlu_conceptual_physics	0.8553
mmlu_econometrics	0.6667
mmlu_electrical_engineering	0.8138
mmlu_elementary_mathematics	0.7778
mmlu_formal_logic	0.6349
mmlu_global_facts	0.4600
mmlu_high_school_biology	0.9290
mmlu_high_school_chemistry	0.7783
mmlu_high_school_computer_science	0.8600
mmlu_high_school_european_history	0.8788
mmlu_high_school_geography	0.9293
mmlu_high_school_government_and_politics	0.9585
mmlu_high_school_macroeconomics	0.8436
mmlu_high_school_mathematics	0.5333
mmlu_high_school_microeconomics	0.9202
mmlu_high_school_physics	0.7086
mmlu_high_school_psychology	0.9303
mmlu_high_school_statistics	0.7870
mmlu_high_school_us_history	0.9020
mmlu_high_school_world_history	0.8861
mmlu_human_aging	0.7803
mmlu_human_sexuality	0.8244
mmlu_humanities	0.6865
mmlu_international_law	0.8595
mmlu_jurisprudence	0.8611
mmlu_logical_fallacies	0.8589
mmlu_machine_learning	0.6518
mmlu_management	0.8544
mmlu_marketing	0.9274
mmlu_medical_genetics	0.9000
mmlu_miscellaneous	0.8914
mmlu_moral_disputes	0.7890
mmlu_moral_scenarios	0.4905
mmlu_nutrition	0.8595
mmlu_other	0.8162
mmlu_philosophy	0.8167
mmlu_prehistory	0.8210
mmlu_professional_accounting	0.6383
mmlu_professional_law	0.5834
mmlu_professional_medicine	0.8971
mmlu_professional_psychology	0.8284
mmlu_public_relations	0.7000
mmlu_security_studies	0.7714
mmlu_social_sciences	0.8616
mmlu_sociology	0.8955
mmlu_stem	0.7691
mmlu_us_foreign_policy	0.9000
mmlu_virology	0.5482
mmlu_world_religions	0.8596
piqa	0.7943

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 = "Qwythos-9B-Claude-Mythos-5-1M-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

bash

vllm serve Qwythos-9B-Claude-Mythos-5-1M-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.

LeaderboardModel1/Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning

Qwythos-9B-Claude-Mythos-5-1M-AutoRound-W4A16-Tuning

Model Details