Quantization made by Richard Erkhov.

Spicy-Laymonade-7B - GGUF

Model creator: https://huggingface.co/ABX-AI/
Original model: https://huggingface.co/ABX-AI/Spicy-Laymonade-7B/

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

Original model description:

base_model: - cgato/TheSpice-7b-v0.1.1 - ABX-AI/Laymonade-7B library_name: transformers tags: - mergekit - merge - not-for-all-audiences license: other

GGUF: https://huggingface.co/ABX-AI/Spicy-Laymonade-7B-GGUF-IQ-Imatrix

Spicy-Laymonade-7B

Well, we have Laymonade, so why not spice it up? This merge is a step into creating a new 9B.

However, I did try it out, and it seemed to work pretty well.

Merge Details

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

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:

slices:
  - sources:
      - model: cgato/TheSpice-7b-v0.1.1
        layer_range: [0, 32]
      - model: ABX-AI/Laymonade-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: ABX-AI/Laymonade-7B
parameters:
  t:
    - filter: self_attn
      value: [0.7, 0.3, 0.6, 0.2, 0.5]
    - filter: mlp
      value: [0.3, 0.7, 0.4, 0.8, 0.5]
    - value: 0.5
dtype: bfloat16