You can deploy this model and start earning money today!

RichardErkhov/
Chat-Error_-_Kimiko-10.7B-v3-gguf

Name: Chat-Error_-_Kimiko-10.7B-v3-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Kimiko-10.7B-v3 - GGUF

Model creator: https://huggingface.co/Chat-Error/
Original model: https://huggingface.co/Chat-Error/Kimiko-10.7B-v3/

Name	Quant method	Size
Kimiko-10.7B-v3.Q2_K.gguf	Q2_K	3.73GB
Kimiko-10.7B-v3.IQ3_XS.gguf	IQ3_XS	4.14GB
Kimiko-10.7B-v3.IQ3_S.gguf	IQ3_S	4.37GB
Kimiko-10.7B-v3.Q3_K_S.gguf	Q3_K_S	4.34GB
Kimiko-10.7B-v3.IQ3_M.gguf	IQ3_M	4.51GB
Kimiko-10.7B-v3.Q3_K.gguf	Q3_K	4.84GB
Kimiko-10.7B-v3.Q3_K_M.gguf	Q3_K_M	4.84GB
Kimiko-10.7B-v3.Q3_K_L.gguf	Q3_K_L	5.26GB
Kimiko-10.7B-v3.IQ4_XS.gguf	IQ4_XS	5.43GB
Kimiko-10.7B-v3.Q4_0.gguf	Q4_0	5.66GB
Kimiko-10.7B-v3.IQ4_NL.gguf	IQ4_NL	5.72GB
Kimiko-10.7B-v3.Q4_K_S.gguf	Q4_K_S	5.7GB
Kimiko-10.7B-v3.Q4_K.gguf	Q4_K	6.02GB
Kimiko-10.7B-v3.Q4_K_M.gguf	Q4_K_M	6.02GB
Kimiko-10.7B-v3.Q4_1.gguf	Q4_1	6.27GB
Kimiko-10.7B-v3.Q5_0.gguf	Q5_0	6.89GB
Kimiko-10.7B-v3.Q5_K_S.gguf	Q5_K_S	6.89GB
Kimiko-10.7B-v3.Q5_K.gguf	Q5_K	7.08GB
Kimiko-10.7B-v3.Q5_K_M.gguf	Q5_K_M	7.08GB
Kimiko-10.7B-v3.Q5_1.gguf	Q5_1	7.51GB
Kimiko-10.7B-v3.Q6_K.gguf	Q6_K	8.2GB
Kimiko-10.7B-v3.Q8_0.gguf	Q8_0	10.62GB

Original model description:

datasets:

nRuaif/Kimiko_v3-v0.1

Experiment model train with my new data. prompt format is Alpaca, you can add (length:tiny), (length:long) to the end of ### Response: to control leng

RichardErkhov/Chat-Error_-_Kimiko-10.7B-v3-gguf

Original model description:

RichardErkhov/
Chat-Error_-_Kimiko-10.7B-v3-gguf