Quantization made by Richard Erkhov.

Configurable-Janus-7B - GGUF

Model creator: https://huggingface.co/vicgalle/
Original model: https://huggingface.co/vicgalle/Configurable-Janus-7B/

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

Original model description:

base_model: - vicgalle/Configurable-Mistral-7B - kaist-ai/janus-dpo-7b library_name: transformers tags: - mergekit - merge license: mit

merge

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

Merge Details

Merge Method

This model was merged using the linear 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: vicgalle/Configurable-Mistral-7B
    parameters:
      weight: 1.0
  - model: kaist-ai/janus-dpo-7b
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16