You can deploy this model and start earning money today!

Lewdiculous/
DaturaCookie_7B-GGUF-IQ-Imatrix

Name: DaturaCookie_7B-GGUF-IQ-Imatrix
Availability: InStock

Views

No views yet

This repository hosts GGUF-IQ-Imatrix quants for ResplendentAI/DaturaCookie_7B.

This is a #multimodal model that also has vision capabilities. Read the full card information if that is your use case.

Quants:

python

    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"
    ]

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.

Vision/multimodal capabilities:

Click here to see how this would work in practice in a roleplay chat.

Click here to see what your SillyTavern Image Captions extension settings should look like.

If you want to use vision functionality:

Make sure you are using the latest version of KoboldCpp.

To use the multimodal capabilities of this model, such as vision, you also need to load the specified mmproj file, you can get it here, it's also hosted in this repository inside the mmproj folder.

You can load the mmproj by using the corresponding section in the interface:

For CLI users, you can load the mmproj file by adding the respective flag to your usual command:

--mmproj your-mmproj-file.gguf

Quantization information:

Steps performed:

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

Using the latest llama.cpp at the time.

Original model information:

DaturaCookie

Proficient at roleplaying and lightehearted conversation, this model is prone to NSFW outputs.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

slices:
  - sources:
      - model: ChaoticNeutrals/Cookie_7B
        layer_range: [0, 32]
      - model: ResplendentAI/Datura_7B
        layer_range: [0, 32]
merge_method: slerp
base_model: ResplendentAI/Datura_7B
parameters:
  t:
    - filter: self_attn
      value: [1, 0.75, 0.5, 0.25, 0]
    - filter: mlp
      value: [0, 0.25, 0.5, 0.75, 1]
    - value: 0.5
dtype: bfloat16

Lewdiculous/DaturaCookie_7B-GGUF-IQ-Imatrix