RichardErkhov/appvoid_-_arco-augment-3-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

arco-augment-3 - GGUF

• Model creator: https://huggingface.co/appvoid/
• Original model: https://huggingface.co/appvoid/arco-augment-3/

Name	Quant method	Size
arco-augment-3.Q2_K.gguf	Q2_K	0.25GB
arco-augment-3.IQ3_XS.gguf	IQ3_XS	0.27GB
arco-augment-3.IQ3_S.gguf	IQ3_S	0.29GB
arco-augment-3.Q3_K_S.gguf	Q3_K_S	0.29GB
arco-augment-3.IQ3_M.gguf	IQ3_M	0.3GB
arco-augment-3.Q3_K.gguf	Q3_K	0.31GB
arco-augment-3.Q3_K_M.gguf	Q3_K_M	0.31GB
arco-augment-3.Q3_K_L.gguf	Q3_K_L	0.34GB
arco-augment-3.IQ4_XS.gguf	IQ4_XS	0.35GB
arco-augment-3.Q4_0.gguf	Q4_0	0.36GB
arco-augment-3.IQ4_NL.gguf	IQ4_NL	0.36GB
arco-augment-3.Q4_K_S.gguf	Q4_K_S	0.37GB
arco-augment-3.Q4_K.gguf	Q4_K	0.38GB
arco-augment-3.Q4_K_M.gguf	Q4_K_M	0.38GB
arco-augment-3.Q4_1.gguf	Q4_1	0.4GB
arco-augment-3.Q5_0.gguf	Q5_0	0.44GB
arco-augment-3.Q5_K_S.gguf	Q5_K_S	0.44GB
arco-augment-3.Q5_K.gguf	Q5_K	0.44GB
arco-augment-3.Q5_K_M.gguf	Q5_K_M	0.44GB
arco-augment-3.Q5_1.gguf	Q5_1	0.47GB
arco-augment-3.Q6_K.gguf	Q6_K	0.51GB
arco-augment-3.Q8_0.gguf	Q8_0	0.66GB

Original model description:

base_model:

• appvoid/arco
• appvoid/arco-2 library_name: transformers tags:
• mergekit
• merge

---

arco-augment-3

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• appvoid/arco
• appvoid/arco-2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: appvoid/arco
      layer_range: [0, 16]
  - sources:
    - model: appvoid/arco-2
      layer_range: [10, 16]

merge_method: passthrough
dtype: float16