Prima-LelantaclesV6.69-7b-GGUF-IQ-Imatrix

This repository hosts GGUF-IQ-Imatrix quantizations for Nitral-AI/Prima-LelantaclesV6.69-7b.

What does "Imatrix" mean?

It stands for Importance Matrix, a technique used to improve the quality of quantized models. The Imatrix is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse. [1] [2]

For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used, you can find it here.

Steps:

Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)

Quants:

    quantization_options = [
        "Q4_K_M", "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
        "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
    ]

If you want anything that's not here or another model, feel free to request.

Original model information:

Note: Its not perfect, but damn is it good when it works.

Models Merged

The following models were included in the merge:

• Test157t/Prima-LelantaclesV6.1M7-7b
• Test157t/Prima-LelantaclesV6.3-7b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Test157t/Prima-LelantaclesV6.1M7-7b
        layer_range: [0, 32]
      - model: Test157t/Prima-LelantaclesV6.3-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Prima-LelantaclesV6.1M7-7b
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: bfloat16