---
base_model: LeroyDyer/Mixtral_AI_MiniTronVision
language:
- en
library_name: transformers
tags:
- 4-bit
- AWQ
- text-generation
- autotrain_compatible
- endpoints_compatible
- vision
pipeline_tag: image-text-to-text
inference: false
quantized_by: Suparious
---
# LeroyDyer/Mixtral_AI_MiniTronVision AWQ

- Model creator: [LeroyDyer](https://huggingface.co./LeroyDyer)
- Original model: [Mixtral_AI_MiniTronVision](https://huggingface.co./LeroyDyer/Mixtral_AI_MiniTronVision)

## Model Summary

# ADD HEAD

```



print('Add Vision...')
# ADD HEAD
# Combine pre-trained encoder and pre-trained decoder to form a Seq2Seq model



Vmodel = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(
    "google/vit-base-patch16-224-in21k", "LeroyDyer/Mixtral_AI_Tiny"
)
_Encoder_ImageProcessor = Vmodel.encoder
_Decoder_ImageTokenizer = Vmodel.decoder
_VisionEncoderDecoderModel = Vmodel
# Add Pad tokems
LM_MODEL.VisionEncoderDecoder = _VisionEncoderDecoderModel
# Add Sub Components
LM_MODEL.Encoder_ImageProcessor = _Encoder_ImageProcessor
LM_MODEL.Decoder_ImageTokenizer = _Decoder_ImageTokenizer
LM_MODEL


```