Edit model card

This repository hosts GGUF-IQ-Imatrix quantizations for Nitral-AI/Infinitely-Laydiculous-9B.

Huge thanks to @Nitral-AI for merging this one.

Instruct format, context size, samplers:

  • Extended Alpaca (recommended) format, for more information check the main base model card here.

  • The expected --contextsize this model can handle is 8192.

  • SillyTavern - TextGen/Samplers.

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. This was just to add a bit more diversity to the data.

Steps:

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

Using the latest llama.cpp at the time.

Quants:

    quantization_options = [
        "Q4_K_M", "Q4_K_S", "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:

image/jpeg

This model was merged using the passthrough 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: Endevor/InfinityRP-v1-7B
        layer_range: [0, 20]
  - sources:
      - model: l3utterfly/mistral-7b-v0.1-layla-v4
        layer_range: [12, 32]
merge_method: passthrough
dtype: float16
Downloads last month
610
GGUF
Model size
8.99B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Unable to determine this model’s pipeline type. Check the docs .

Merge of

Collection including Lewdiculous/Infinitely-Laydiculous-9B-GGUF-IQ-Imatrix