ABX-AI/Infinite-Sumika-9B-GGUF-IQ-Imatrix

GGUF / IQ / Imatrix for Infinite-Sumika-9B

Why Importance Matrix?

Importance Matrix, at least based on my testing, has shown to improve the output and performance of "IQ"-type quantizations, where the compression becomes quite heavy. The Imatrix performs a calibration, using a provided dataset. Testing has shown that semi-randomized data can help perserve more important segments as the compression is applied.

Related discussions in Github: [1] [2]

The imatrix.txt file that I used contains general, semi-random data, with some added extra kink.

Infinite-Sumika-9B

This model is intended for fictional role-playing and storywriting.

It seems to be doing good with longer text, and prefers to write longer, storytelling-like responses sometimes.

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:

• localfultonextractor/Erosumika-7B-v2
• Endevor/InfinityRP-v1-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Endevor/InfinityRP-v1-7B
        layer_range: [0, 20]
  - sources:
      - model: localfultonextractor/Erosumika-7B-v2
        layer_range: [12, 32]
merge_method: passthrough
dtype: float16