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

GGUF / IQ / Imatrix for Infinite-Laymons-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 custom kink.

Infinite-Laymons-9B

Infinite-Laymons-9B is intended for fictional role-play and storytelling.

The focus is on original responses and elimitation, or reduction of refusals.

Merge Details

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

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• Nitral-AI/Infinitely-Laydiculous-7B
• ABX-AI/Infinite-Laymons-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Nitral-AI/Infinitely-Laydiculous-7B
        layer_range: [0, 20]
  - sources:
      - model: ABX-AI/Infinite-Laymons-7B
        layer_range: [12, 32]
merge_method: passthrough
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.29
AI2 Reasoning Challenge (25-Shot)	65.61
HellaSwag (10-Shot)	84.14
MMLU (5-Shot)	64.53
TruthfulQA (0-shot)	54.87
Winogrande (5-shot)	80.82
GSM8k (5-shot)	53.75