RichardErkhov/mohomin123_-_M-DIE-M-10.7B-gguf

Quantization made by Richard Erkhov.

M-DIE-M-10.7B - GGUF

Model creator: https://huggingface.co/mohomin123/
Original model: https://huggingface.co/mohomin123/M-DIE-M-10.7B/

Name	Quant method	Size
M-DIE-M-10.7B.Q2_K.gguf	Q2_K	3.73GB
M-DIE-M-10.7B.IQ3_XS.gguf	IQ3_XS	4.14GB
M-DIE-M-10.7B.IQ3_S.gguf	IQ3_S	4.37GB
M-DIE-M-10.7B.Q3_K_S.gguf	Q3_K_S	4.34GB
M-DIE-M-10.7B.IQ3_M.gguf	IQ3_M	4.51GB
M-DIE-M-10.7B.Q3_K.gguf	Q3_K	4.84GB
M-DIE-M-10.7B.Q3_K_M.gguf	Q3_K_M	4.84GB
M-DIE-M-10.7B.Q3_K_L.gguf	Q3_K_L	5.26GB
M-DIE-M-10.7B.IQ4_XS.gguf	IQ4_XS	5.43GB
M-DIE-M-10.7B.Q4_0.gguf	Q4_0	5.66GB
M-DIE-M-10.7B.IQ4_NL.gguf	IQ4_NL	5.72GB
M-DIE-M-10.7B.Q4_K_S.gguf	Q4_K_S	5.7GB
M-DIE-M-10.7B.Q4_K.gguf	Q4_K	6.02GB
M-DIE-M-10.7B.Q4_K_M.gguf	Q4_K_M	6.02GB
M-DIE-M-10.7B.Q4_1.gguf	Q4_1	6.27GB
M-DIE-M-10.7B.Q5_0.gguf	Q5_0	6.89GB
M-DIE-M-10.7B.Q5_K_S.gguf	Q5_K_S	6.89GB
M-DIE-M-10.7B.Q5_K.gguf	Q5_K	7.08GB
M-DIE-M-10.7B.Q5_K_M.gguf	Q5_K_M	7.08GB
M-DIE-M-10.7B.Q5_1.gguf	Q5_1	7.51GB
M-DIE-M-10.7B.Q6_K.gguf	Q6_K	8.2GB
M-DIE-M-10.7B.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: cc-by-nc-sa-4.0 language: - en - ko

Data Is Everything.

To try other models(involving commercial-available model), please check out our Demo Page(🔨constructing)

This model is made by Ados based on upstage/SOLAR-10.7B-Instruct-v1.0.

Train Dataset

Dataset used for training is collected primarily from huggingface and utilized using our own translation model.

Language
- KR 73%
- EN 24%
- Others 3%
Type
- single turn QA (alpaca style) 29%
- multi turn QA (vicuna style) 21%
- instructed QA 26%
- summary 12%
- translation 12%

After collecting data, we removed low quality rows. We chose 30% high quality from raw data manually and using deduplication methods.

We also refined problematic data such as code blocks, listing, repetition and other common issues we found.

Prompt template

### System:
You are an AI assistant, please behave and help the user. Your name is OLLM(오름) by Ados(주식회사아도스), OLLM stands for On-premise LLM.

### User: On-premise LLM이 뭔가요?

### Assistant:

For more informations, please contact us.

To try other models(involving commercial-available model), please check out our Demo Page(🔨constructing)

License

upstage/SOLAR-10.7B-Instruct-v1.0: cc-by-nc-4.0
- Since some non-commercial datasets such as Alpaca are used for fine-tuning, we release this model as cc-by-nc-4.0.

@misc{kim2023solar,
      title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling}, 
      author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim},
      year={2023},
      eprint={2312.15166},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}