RichardErkhov/megastudyedu_-_ME-7B-v1.0-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ME-7B-v1.0 - GGUF

• Model creator: https://huggingface.co/megastudyedu/
• Original model: https://huggingface.co/megastudyedu/ME-7B-v1.0/

Name	Quant method	Size
ME-7B-v1.0.Q2_K.gguf	Q2_K	2.53GB
ME-7B-v1.0.IQ3_XS.gguf	IQ3_XS	2.81GB
ME-7B-v1.0.IQ3_S.gguf	IQ3_S	2.96GB
ME-7B-v1.0.Q3_K_S.gguf	Q3_K_S	2.95GB
ME-7B-v1.0.IQ3_M.gguf	IQ3_M	3.06GB
ME-7B-v1.0.Q3_K.gguf	Q3_K	3.28GB
ME-7B-v1.0.Q3_K_M.gguf	Q3_K_M	3.28GB
ME-7B-v1.0.Q3_K_L.gguf	Q3_K_L	3.56GB
ME-7B-v1.0.IQ4_XS.gguf	IQ4_XS	3.67GB
ME-7B-v1.0.Q4_0.gguf	Q4_0	3.83GB
ME-7B-v1.0.IQ4_NL.gguf	IQ4_NL	3.87GB
ME-7B-v1.0.Q4_K_S.gguf	Q4_K_S	3.86GB
ME-7B-v1.0.Q4_K.gguf	Q4_K	4.07GB
ME-7B-v1.0.Q4_K_M.gguf	Q4_K_M	4.07GB
ME-7B-v1.0.Q4_1.gguf	Q4_1	4.24GB
ME-7B-v1.0.Q5_0.gguf	Q5_0	4.65GB
ME-7B-v1.0.Q5_K_S.gguf	Q5_K_S	4.65GB
ME-7B-v1.0.Q5_K.gguf	Q5_K	4.78GB
ME-7B-v1.0.Q5_K_M.gguf	Q5_K_M	4.78GB
ME-7B-v1.0.Q5_1.gguf	Q5_1	5.07GB
ME-7B-v1.0.Q6_K.gguf	Q6_K	5.53GB
ME-7B-v1.0.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-nd-4.0 language: - ko

Model Card for ME-7B-v1.0

Developed by : 메가스터디교육, 프리딕션, 마이스

Base Model : jondurbin/bagel-dpo-7b-v0.1

사용 데이터셋

• jondurbin/bagel-v0.3 SFT 번역 데이터셋(translated by megastudyedu/ME-7B-v1.0)
• megastudy/M-SOLAR-10.7B-v1.3 데이터