Quantization made by Richard Erkhov.

arco-salad-1 - GGUF

Model creator: https://huggingface.co/appvoid/
Original model: https://huggingface.co/appvoid/arco-salad-1/

Name	Quant method	Size
arco-salad-1.Q2_K.gguf	Q2_K	0.2GB
arco-salad-1.IQ3_XS.gguf	IQ3_XS	0.22GB
arco-salad-1.IQ3_S.gguf	IQ3_S	0.22GB
arco-salad-1.Q3_K_S.gguf	Q3_K_S	0.22GB
arco-salad-1.IQ3_M.gguf	IQ3_M	0.23GB
arco-salad-1.Q3_K.gguf	Q3_K	0.24GB
arco-salad-1.Q3_K_M.gguf	Q3_K_M	0.24GB
arco-salad-1.Q3_K_L.gguf	Q3_K_L	0.26GB
arco-salad-1.IQ4_XS.gguf	IQ4_XS	0.27GB
arco-salad-1.Q4_0.gguf	Q4_0	0.28GB
arco-salad-1.IQ4_NL.gguf	IQ4_NL	0.28GB
arco-salad-1.Q4_K_S.gguf	Q4_K_S	0.28GB
arco-salad-1.Q4_K.gguf	Q4_K	0.3GB
arco-salad-1.Q4_K_M.gguf	Q4_K_M	0.3GB
arco-salad-1.Q4_1.gguf	Q4_1	0.31GB
arco-salad-1.Q5_0.gguf	Q5_0	0.34GB
arco-salad-1.Q5_K_S.gguf	Q5_K_S	0.34GB
arco-salad-1.Q5_K.gguf	Q5_K	0.34GB
arco-salad-1.Q5_K_M.gguf	Q5_K_M	0.34GB
arco-salad-1.Q5_1.gguf	Q5_1	0.36GB
arco-salad-1.Q6_K.gguf	Q6_K	0.39GB
arco-salad-1.Q8_0.gguf	Q8_0	0.51GB

Original model description:

base_model:

appvoid/arco
appvoid/arco-interpreter-v1.2
appvoid/arco-2 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 TIES merge method using appvoid/arco as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: appvoid/arco-interpreter-v1.2
    parameters:
      density: 0.5
      weight: 0.5
  - model: appvoid/arco-2
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: appvoid/arco
parameters:
  normalize: false
  int8_mask: true
dtype: float16