Hugging Face's logo

Lewdiculous
/
Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix

GGUF
quantized
roleplay
multimodal
vision
sillytavern
Merge
mistral
Inference Endpoints
Model card Files Community
1
Eris_PrimeV3-Vision-7B-GGUF-IQ-Imatrix / README.md
Lewdiculous's picture
Lewdiculous
Update README.md
1ab50a6 verified
preview code
|
raw
history blame contribute delete
4.02 kB
metadata
license: other
tags:
  - gguf
  - quantized
  - roleplay
  - multimodal
  - vision
  - sillytavern
  - merge
  - mistral

This repository hosts GGUF-IQ-Imatrix quants for ChaoticNeutrals/Eris_PrimeV3-Vision-7B.

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

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"
    ]

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.

image/jpeg


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

image/jpeg


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.

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

image/png

  • 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:

image/png

Eris with vision capabilites supported by KCPP (required for vision support): https://huggingface.co./koboldcpp/mmproj/blob/main/mistral-7b-mmproj-v1.5-Q4_1.gguf

This model was merged using the SLERP 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: ChaoticNeutrals/Eris_Prime-V2-7B
        layer_range: [0, 32]
      - model: InferenceIllusionist/Excalibur-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: ChaoticNeutrals/Eris_Prime-V2-7B
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