|
--- |
|
inference: false |
|
tags: |
|
- gguf |
|
- quantized |
|
- roleplay |
|
- multimodal |
|
- vision |
|
- llava |
|
- sillytavern |
|
- merge |
|
- mistral |
|
- conversational |
|
base_model: |
|
- grimjim/kukulemon-7B |
|
- Inv/Konstanta-V4-Alpha-7B |
|
--- |
|
# #Roleplay #Multimodal #Vision |
|
|
|
This repository hosts GGUF-IQ-Imatrix quants for [Nitral-AI/KukulStanta-7B](https://huggingface.co/Nitral-AI/KukulStanta-7B). |
|
|
|
"Good performer in the Chaiverse leaderboard. There have been big changes to the evaluation rules since then, but the model is a good performer." |
|
|
|
**Recommended starting [SillyTavern presets here](https://huggingface.co/Lewdiculous/Eris_PrimeV4-Vision-32k-7B-GGUF-IQ-Imatrix/tree/main/sillytavern-presets-lewdicu-3.0.2-mistral-0.2).** |
|
|
|
This is a **#multimodal** model that also has **#vision** capabilities. <br> Read the full card information if you also want to use that functionality. |
|
|
|
 |
|
|
|
**What does "Imatrix" mean?** |
|
|
|
<details><summary> |
|
⇲ Click here to expand/hide more information about this topic. |
|
</summary> |
|
|
|
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. |
|
|
|
</details><br> |
|
|
|
# Vision/multimodal capabilities: |
|
|
|
<details><summary> |
|
⇲ Click here to expand/hide how this would work in practice in a roleplay chat. |
|
</summary> |
|
|
|
 |
|
|
|
</details><br> |
|
|
|
<details><summary> |
|
⇲ Click here to expand/hide 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) or as uploaded in the repository. |
|
|
|
* 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: |
|
|
|
|
|
<details><summary> |
|
⇲ Click here to expand/hide more information about this topic. |
|
</summary> |
|
|
|
```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" |
|
] |
|
``` |
|
|
|
**Steps performed:** |
|
|
|
``` |
|
Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) |
|
``` |
|
*Using the latest llama.cpp at the time.* |
|
|
|
</details><br> |
