RichardErkhov/appvoid_-_arco-exp-01-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

arco-exp-01 - GGUF

• Model creator: https://huggingface.co/appvoid/
• Original model: https://huggingface.co/appvoid/arco-exp-01/

Name	Quant method	Size
arco-exp-01.Q2_K.gguf	Q2_K	0.2GB
arco-exp-01.IQ3_XS.gguf	IQ3_XS	0.22GB
arco-exp-01.IQ3_S.gguf	IQ3_S	0.22GB
arco-exp-01.Q3_K_S.gguf	Q3_K_S	0.22GB
arco-exp-01.IQ3_M.gguf	IQ3_M	0.23GB
arco-exp-01.Q3_K.gguf	Q3_K	0.24GB
arco-exp-01.Q3_K_M.gguf	Q3_K_M	0.24GB
arco-exp-01.Q3_K_L.gguf	Q3_K_L	0.26GB
arco-exp-01.IQ4_XS.gguf	IQ4_XS	0.27GB
arco-exp-01.Q4_0.gguf	Q4_0	0.28GB
arco-exp-01.IQ4_NL.gguf	IQ4_NL	0.28GB
arco-exp-01.Q4_K_S.gguf	Q4_K_S	0.28GB
arco-exp-01.Q4_K.gguf	Q4_K	0.3GB
arco-exp-01.Q4_K_M.gguf	Q4_K_M	0.3GB
arco-exp-01.Q4_1.gguf	Q4_1	0.31GB
arco-exp-01.Q5_0.gguf	Q5_0	0.34GB
arco-exp-01.Q5_K_S.gguf	Q5_K_S	0.34GB
arco-exp-01.Q5_K.gguf	Q5_K	0.34GB
arco-exp-01.Q5_K_M.gguf	Q5_K_M	0.34GB
arco-exp-01.Q5_1.gguf	Q5_1	0.36GB
arco-exp-01.Q6_K.gguf	Q6_K	0.39GB
arco-exp-01.Q8_0.gguf	Q8_0	0.51GB

Original model description:

base_model:

• appvoid/massive
• appvoid/text-arco 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:

• appvoid/massive
• appvoid/text-arco

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: appvoid/text-arco
        layer_range: [0, 16]
      - model: appvoid/massive
        layer_range: [0, 16]
merge_method: slerp
base_model: appvoid/text-arco
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: float16