Quantization made by Richard Erkhov.

MT-Merge1-BI-gemma-2-9B - GGUF

Model creator: https://huggingface.co/zelk12/
Original model: https://huggingface.co/zelk12/MT-Merge1-BI-gemma-2-9B/

Name	Quant method	Size
MT-Merge1-BI-gemma-2-9B.Q2_K.gguf	Q2_K	3.54GB
MT-Merge1-BI-gemma-2-9B.IQ3_XS.gguf	IQ3_XS	3.86GB
MT-Merge1-BI-gemma-2-9B.IQ3_S.gguf	IQ3_S	4.04GB
MT-Merge1-BI-gemma-2-9B.Q3_K_S.gguf	Q3_K_S	4.04GB
MT-Merge1-BI-gemma-2-9B.IQ3_M.gguf	IQ3_M	4.19GB
MT-Merge1-BI-gemma-2-9B.Q3_K.gguf	Q3_K	4.43GB
MT-Merge1-BI-gemma-2-9B.Q3_K_M.gguf	Q3_K_M	4.43GB
MT-Merge1-BI-gemma-2-9B.Q3_K_L.gguf	Q3_K_L	4.78GB
MT-Merge1-BI-gemma-2-9B.IQ4_XS.gguf	IQ4_XS	4.86GB
MT-Merge1-BI-gemma-2-9B.Q4_0.gguf	Q4_0	5.07GB
MT-Merge1-BI-gemma-2-9B.IQ4_NL.gguf	IQ4_NL	5.1GB
MT-Merge1-BI-gemma-2-9B.Q4_K_S.gguf	Q4_K_S	5.1GB
MT-Merge1-BI-gemma-2-9B.Q4_K.gguf	Q4_K	5.37GB
MT-Merge1-BI-gemma-2-9B.Q4_K_M.gguf	Q4_K_M	5.37GB
MT-Merge1-BI-gemma-2-9B.Q4_1.gguf	Q4_1	5.55GB
MT-Merge1-BI-gemma-2-9B.Q5_0.gguf	Q5_0	6.04GB
MT-Merge1-BI-gemma-2-9B.Q5_K_S.gguf	Q5_K_S	6.04GB
MT-Merge1-BI-gemma-2-9B.Q5_K.gguf	Q5_K	6.19GB
MT-Merge1-BI-gemma-2-9B.Q5_K_M.gguf	Q5_K_M	6.19GB
MT-Merge1-BI-gemma-2-9B.Q5_1.gguf	Q5_1	6.52GB
MT-Merge1-BI-gemma-2-9B.Q6_K.gguf	Q6_K	7.07GB
MT-Merge1-BI-gemma-2-9B.Q8_0.gguf	Q8_0	9.15GB

Original model description:

base_model:

zelk12/MT-Merge1-BB-gemma-2-MT1g1MT5g1-9B
zelk12/MT-Merge1-IF-gemma-2-MT1g1MT4g1-9B library_name: transformers tags:
mergekit
merge

merge

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:

models:
  - model: zelk12/MT-Merge1-BB-gemma-2-MT1g1MT5g1-9B
  - model: zelk12/MT-Merge1-IF-gemma-2-MT1g1MT4g1-9B
merge_method: slerp
base_model: zelk12/MT-Merge1-BB-gemma-2-MT1g1MT5g1-9B
dtype: bfloat16
parameters:
  t: 0.5