You can deploy this model and start earning money today!

RichardErkhov/
JY623_-_KoSOLRA-10.7B-merge-v2.2-gguf

Name: JY623_-_KoSOLRA-10.7B-merge-v2.2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

KoSOLRA-10.7B-merge-v2.2 - GGUF

Model creator: https://huggingface.co/JY623/
Original model: https://huggingface.co/JY623/KoSOLRA-10.7B-merge-v2.2/

Name	Quant method	Size
KoSOLRA-10.7B-merge-v2.2.Q2_K.gguf	Q2_K	3.73GB
KoSOLRA-10.7B-merge-v2.2.IQ3_XS.gguf	IQ3_XS	4.14GB
KoSOLRA-10.7B-merge-v2.2.IQ3_S.gguf	IQ3_S	4.37GB
KoSOLRA-10.7B-merge-v2.2.Q3_K_S.gguf	Q3_K_S	4.34GB
KoSOLRA-10.7B-merge-v2.2.IQ3_M.gguf	IQ3_M	4.51GB
KoSOLRA-10.7B-merge-v2.2.Q3_K.gguf	Q3_K	4.84GB
KoSOLRA-10.7B-merge-v2.2.Q3_K_M.gguf	Q3_K_M	4.84GB
KoSOLRA-10.7B-merge-v2.2.Q3_K_L.gguf	Q3_K_L	5.26GB
KoSOLRA-10.7B-merge-v2.2.IQ4_XS.gguf	IQ4_XS	5.43GB
KoSOLRA-10.7B-merge-v2.2.Q4_0.gguf	Q4_0	5.66GB
KoSOLRA-10.7B-merge-v2.2.IQ4_NL.gguf	IQ4_NL	5.72GB
KoSOLRA-10.7B-merge-v2.2.Q4_K_S.gguf	Q4_K_S	5.7GB
KoSOLRA-10.7B-merge-v2.2.Q4_K.gguf	Q4_K	6.02GB
KoSOLRA-10.7B-merge-v2.2.Q4_K_M.gguf	Q4_K_M	6.02GB
KoSOLRA-10.7B-merge-v2.2.Q4_1.gguf	Q4_1	6.27GB
KoSOLRA-10.7B-merge-v2.2.Q5_0.gguf	Q5_0	6.89GB
KoSOLRA-10.7B-merge-v2.2.Q5_K_S.gguf	Q5_K_S	6.89GB
KoSOLRA-10.7B-merge-v2.2.Q5_K.gguf	Q5_K	7.08GB
KoSOLRA-10.7B-merge-v2.2.Q5_K_M.gguf	Q5_K_M	7.08GB
KoSOLRA-10.7B-merge-v2.2.Q5_1.gguf	Q5_1	7.51GB
KoSOLRA-10.7B-merge-v2.2.Q6_K.gguf	Q6_K	8.2GB
KoSOLRA-10.7B-merge-v2.2.Q8_0.gguf	Q8_0	10.62GB

Original model description:

base_model:

JY623/KoSOLAR-10.7B-merge-v2.0
rrw-x2/KoSOLAR-10.7B-v2.1 library_name: transformers tags:
mergekit
merge license: apache-2.0

merge_base_ft_2

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:

  - sources:

      - model: JY623/KoSOLAR-10.7B-merge-v2.0

        layer_range: [0, 48]

      - model: rrw-x2/KoSOLAR-10.7B-v2.1

        layer_range: [0, 48]

merge_method: slerp
base_model: JY623/KoSOLAR-10.7B-merge-v2.0

parameters:
  t: 0.2

dtype: bfloat16

RichardErkhov/JY623_-_KoSOLRA-10.7B-merge-v2.2-gguf