RichardErkhov/Andron00e_-_YetAnother_Open-Llama-3B-LoRA-OpenOrca-gguf

Quantization made by Richard Erkhov.

YetAnother_Open-Llama-3B-LoRA-OpenOrca - GGUF

Model creator: https://huggingface.co/Andron00e/
Original model: https://huggingface.co/Andron00e/YetAnother_Open-Llama-3B-LoRA-OpenOrca/

Name	Quant method	Size
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q2_K.gguf	Q2_K	1.84GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.IQ3_XS.gguf	IQ3_XS	1.84GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.IQ3_S.gguf	IQ3_S	1.84GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q3_K_S.gguf	Q3_K_S	1.84GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.IQ3_M.gguf	IQ3_M	1.92GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q3_K.gguf	Q3_K	1.99GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q3_K_M.gguf	Q3_K_M	1.99GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q3_K_L.gguf	Q3_K_L	2.06GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.IQ4_XS.gguf	IQ4_XS	1.86GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q4_0.gguf	Q4_0	1.84GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.IQ4_NL.gguf	IQ4_NL	1.86GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q4_K_S.gguf	Q4_K_S	2.24GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q4_K.gguf	Q4_K	2.4GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q4_K_M.gguf	Q4_K_M	2.4GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q4_1.gguf	Q4_1	2.04GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q5_0.gguf	Q5_0	2.23GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q5_K_S.gguf	Q5_K_S	2.42GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q5_K.gguf	Q5_K	2.57GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q5_K_M.gguf	Q5_K_M	2.57GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q5_1.gguf	Q5_1	2.42GB
YetAnother_Open-Llama-3B-LoRA-OpenOrca.Q6_K.gguf	Q6_K	3.39GB

Original model description:

license: apache-2.0 datasets: - Open-Orca/OpenOrca language: - en library_name: transformers pipeline_tag: question-answering metrics: - accuracy

Model Details

Model Description

Developed by: Andron00e
Language(s) (NLP): Python (PyTorch, transformers, peft)
License: apache-2.0
Finetuned from model: openlm-research/open_llama_3b

Model Sources [optional]

Repository: https://github.com/Andron00e/Fine-Tuning-project

Training Data

https://huggingface.co/datasets/Open-Orca/OpenOrca

Evaluation

Evaluation of the model was carried out using EulerAI library, more precisely

Testing Data

hellaswag testing dataset

Metrics

Accuracy

Results and Model Examination

Task	Version	Metric	Value		Stderr
hellaswag	0	acc	0.4899	±	0.0050
		acc_norm	0.6506	±	0.0048

Citations

@software{openlm2023openllama,
  author = {Geng, Xinyang and Liu, Hao},
  title = {OpenLLaMA: An Open Reproduction of LLaMA},
  month = May,
  year = 2023,
  url = {https://github.com/openlm-research/open_llama}
}

@software{eval-harness,
  author       = {Gao, Leo and
                  Tow, Jonathan and
                  Biderman, Stella and
                  Black, Sid and
                  DiPofi, Anthony and
                  Foster, Charles and
                  Golding, Laurence and
                  Hsu, Jeffrey and
                  McDonell, Kyle and
                  Muennighoff, Niklas and
                  Phang, Jason and
                  Reynolds, Laria and
                  Tang, Eric and
                  Thite, Anish and
                  Wang, Ben and
                  Wang, Kevin and
                  Zou, Andy},
  title        = {A framework for few-shot language model evaluation},
  month        = sep,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {v0.0.1},
  doi          = {10.5281/zenodo.5371628},
  url          = {https://doi.org/10.5281/zenodo.5371628}
}

Model Card Authors and Contact

Andron00e