Hugging Face's logo

solidrust
/
Mixtral_AI_TinyTronVision-AWQ

Text Generation
Transformers
Safetensors
English
mistral
4-bit precision
AWQ
Inference Endpoints
vision
text-generation-inference
awq
Model card Files Community
Mixtral_AI_TinyTronVision-AWQ / README.md
Suparious's picture
Suparious
Added base_model tag in README.md
3a4ff96 verified
preview code
|
raw
history blame
1.12 kB
metadata
base_model: LeroyDyer/Mixtral_AI_TinyTronVision
license: mit
language:
  - en
library_name: transformers
tags:
  - 4-bit
  - AWQ
  - text-generation
  - autotrain_compatible
  - endpoints_compatible
  - vision
pipeline_tag: text-generation
inference: false
quantized_by: Suparious

LeroyDyer/Mixtral_AI_TinyTronVision AWQ

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