RichardErkhov/AIJUUD_-_juud-Mistral-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

juud-Mistral-7B - GGUF

• Model creator: https://huggingface.co/AIJUUD/
• Original model: https://huggingface.co/AIJUUD/juud-Mistral-7B/

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

Original model description:

library_name: transformers license: apache-2.0

Model Card for Model ID

Welcome To BNK AI.

You now are seeing Initiative status of Huge AI Team like mackintosh Garage company

Though beginning seems humble future will be prosperous!

If you have a question, feel free to contact to bnkaiteam@gmail.com