|
--- |
|
license: other |
|
tags: |
|
- gguf |
|
- quantized |
|
- roleplay |
|
- multimodal |
|
- vision |
|
- sillytavern |
|
- merge |
|
- mistral |
|
--- |
|
This repository hosts GGUF-IQ-Imatrix quants for [ChaoticNeutrals/Eris_PrimeV3-Vision-7B](https://huggingface.co/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: |
|
```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]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) |
|
|
|
For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt). This was just to add a bit more diversity to the data. |
|
|
|
# Vision/multimodal capabilities: |
|
|
|
<details><summary> |
|
Click here to see how this would work in practice in a roleplay chat. |
|
</summary> |
|
|
|
 |
|
|
|
</details><br> |
|
|
|
<details><summary> |
|
Click here to see what your SillyTavern Image Captions extension settings should look like. |
|
</summary> |
|
|
|
 |
|
|
|
</details><br> |
|
|
|
**If you want to use vision functionality:** |
|
|
|
* Make sure you are using the latest version of [KoboldCpp](https://github.com/LostRuins/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](https://huggingface.co/cjpais/llava-1.6-mistral-7b-gguf/blob/main/mmproj-model-f16.gguf). |
|
|
|
* 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: |
|
|
|
 |
|
|
|
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: |
|
* [InferenceIllusionist/Excalibur-7b](https://huggingface.co/InferenceIllusionist/Excalibur-7b) |
|
* [ChaoticNeutrals/Eris_Prime-V2-7B](https://huggingface.co/ChaoticNeutrals/Eris_Prime-V2-7B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
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 |
|
``` |
