|
--- |
|
base_model: |
|
- LeroyDyer/Mixtral_Chat_X_128k |
|
- ChaoticNeutrals/Eris_PrimeV3-Vision-7B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- code |
|
- Cyber-Series |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
- bertscore |
|
- bleurt |
|
- bleu |
|
- code_eval |
|
pipeline_tag: image-text-to-text |
|
--- |
|
# LeroyDyer/Mixtral_AI_Vision_128k |
|
|
|
|
|
This model is also a Vision model with 128k context window: |
|
|
|
To be further refined! Working! |
|
|
|
|
|
|
|
## VISION+ Language Model |
|
|
|
```script |
|
|
|
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. |
|
|
|
https://huggingface.co/LeroyDyer/Mixtral_AI_Vision_128k/blob/main/mmproj-model-f16.gguf |
|
|
|
You can load the mmproj by using the corresponding section in the interface: |
|
|
|
|
|
KoboldCpp now supports Vision via Multimodal Projectors (aka LLaVA), allowing it to perceive and react to images! Load a suitable --mmproj file or select it in the GUI launcher to use vision capabilities. (Not working on Vulkan) |
|
Note: This is NOT limited to only LLaVA models, any compatible model of the same size and architecture can gain vision capabilities! |
|
Simply grab a 200mb mmproj file for your architecture here, |
|
|
|
https://huggingface.co/koboldcpp/mmproj |
|
|
|
load it with --mmproj and stick it into your favorite compatible model, and it will be able to see images as well! |
|
|
|
``` |
|
|
|
|
|
|
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [LeroyDyer/Mixtral_Chat_X_128k](https://huggingface.co/LeroyDyer/Mixtral_Chat_X_128k) |
|
* [ChaoticNeutrals/Eris_PrimeV3-Vision-7B](https://huggingface.co/ChaoticNeutrals/Eris_PrimeV3-Vision-7B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
